Delete checkpoints
Browse files- checkpoints/checkpoint-900/config.json +0 -40
- checkpoints/checkpoint-900/generation_config.json +0 -12
- checkpoints/checkpoint-900/global_step900/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0 -3
- checkpoints/checkpoint-900/global_step900/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0 -3
- checkpoints/checkpoint-900/global_step900/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0 -3
- checkpoints/checkpoint-900/global_step900/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0 -3
- checkpoints/checkpoint-900/global_step900/zero_pp_rank_0_mp_rank_00_model_states.pt +0 -3
- checkpoints/checkpoint-900/global_step900/zero_pp_rank_1_mp_rank_00_model_states.pt +0 -3
- checkpoints/checkpoint-900/global_step900/zero_pp_rank_2_mp_rank_00_model_states.pt +0 -3
- checkpoints/checkpoint-900/global_step900/zero_pp_rank_3_mp_rank_00_model_states.pt +0 -3
- checkpoints/checkpoint-900/latest +0 -1
- checkpoints/checkpoint-900/model.safetensors +0 -3
- checkpoints/checkpoint-900/rng_state_0.pth +0 -3
- checkpoints/checkpoint-900/rng_state_1.pth +0 -3
- checkpoints/checkpoint-900/rng_state_2.pth +0 -3
- checkpoints/checkpoint-900/rng_state_3.pth +0 -3
- checkpoints/checkpoint-900/scheduler.pt +0 -3
- checkpoints/checkpoint-900/special_tokens_map.json +0 -17
- checkpoints/checkpoint-900/tokenizer.json +0 -3
- checkpoints/checkpoint-900/tokenizer_config.json +0 -2064
- checkpoints/checkpoint-900/trainer_state.json +0 -1365
- checkpoints/checkpoint-900/training_args.bin +0 -3
- checkpoints/checkpoint-900/zero_to_fp32.py +0 -674
checkpoints/checkpoint-900/config.json
DELETED
|
@@ -1,40 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "/root/open-r1/checkpoints/meta-llama/Llama-3.2-1B-Instruct/",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"LlamaForCausalLM"
|
| 5 |
-
],
|
| 6 |
-
"attention_bias": false,
|
| 7 |
-
"attention_dropout": 0.0,
|
| 8 |
-
"bos_token_id": 128000,
|
| 9 |
-
"eos_token_id": [
|
| 10 |
-
128001,
|
| 11 |
-
128008,
|
| 12 |
-
128009
|
| 13 |
-
],
|
| 14 |
-
"head_dim": 64,
|
| 15 |
-
"hidden_act": "silu",
|
| 16 |
-
"hidden_size": 2048,
|
| 17 |
-
"initializer_range": 0.02,
|
| 18 |
-
"intermediate_size": 8192,
|
| 19 |
-
"max_position_embeddings": 131072,
|
| 20 |
-
"mlp_bias": false,
|
| 21 |
-
"model_type": "llama",
|
| 22 |
-
"num_attention_heads": 32,
|
| 23 |
-
"num_hidden_layers": 16,
|
| 24 |
-
"num_key_value_heads": 8,
|
| 25 |
-
"pretraining_tp": 1,
|
| 26 |
-
"rms_norm_eps": 1e-05,
|
| 27 |
-
"rope_scaling": {
|
| 28 |
-
"factor": 32.0,
|
| 29 |
-
"high_freq_factor": 4.0,
|
| 30 |
-
"low_freq_factor": 1.0,
|
| 31 |
-
"original_max_position_embeddings": 8192,
|
| 32 |
-
"rope_type": "llama3"
|
| 33 |
-
},
|
| 34 |
-
"rope_theta": 500000.0,
|
| 35 |
-
"tie_word_embeddings": true,
|
| 36 |
-
"torch_dtype": "bfloat16",
|
| 37 |
-
"transformers_version": "4.49.0.dev0",
|
| 38 |
-
"use_cache": false,
|
| 39 |
-
"vocab_size": 128256
|
| 40 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/generation_config.json
DELETED
|
@@ -1,12 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token_id": 128000,
|
| 3 |
-
"do_sample": true,
|
| 4 |
-
"eos_token_id": [
|
| 5 |
-
128001,
|
| 6 |
-
128008,
|
| 7 |
-
128009
|
| 8 |
-
],
|
| 9 |
-
"temperature": 0.6,
|
| 10 |
-
"top_p": 0.9,
|
| 11 |
-
"transformers_version": "4.49.0.dev0"
|
| 12 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/global_step900/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:7d6bf6cee495523ac6fc19c1ae85cc66c0402e494e79e8273ee9223bacd1f0c2
|
| 3 |
-
size 3707447984
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/global_step900/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:12ff302b03e315bc3dadefc12b331b9d8f441c2d434dcd7ace6988b3a4899bbf
|
| 3 |
-
size 3707447984
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/global_step900/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e89cb27bfc2b714613219126b07eee6a1dd5339104061549056618ffcfbc31d3
|
| 3 |
-
size 3707447984
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/global_step900/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:65b65a4e29c8aefc1a051b7ce234d0897d40280fc01c4e2bbcc91e86037881dc
|
| 3 |
-
size 3707447984
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/global_step900/zero_pp_rank_0_mp_rank_00_model_states.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f4f0586d4eeef8444a5875b013789df4929aca9fc3d6e79715825bb5eff91ab2
|
| 3 |
-
size 75384
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/global_step900/zero_pp_rank_1_mp_rank_00_model_states.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:602896dfa0ba233ca45d33ebba6047a7b959d7bed67329f29ca4b1395486af8d
|
| 3 |
-
size 75320
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/global_step900/zero_pp_rank_2_mp_rank_00_model_states.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:c4e64bfaae681ce6019b60875fd5f3513a6ce2d5d3beb8c4dad8ff3c68f3905d
|
| 3 |
-
size 75320
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/global_step900/zero_pp_rank_3_mp_rank_00_model_states.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a9dcb5835d47b7453eb34258d7b6589f5b17eb159d2e2d3a96193cd34077e161
|
| 3 |
-
size 75320
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/latest
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
global_step900
|
|
|
|
|
|
checkpoints/checkpoint-900/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:084a75537bb0b59dce7c866406a247d7976305d52645a56edc44b8e8f755c30f
|
| 3 |
-
size 2471645608
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/rng_state_0.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:ae78313eb528c8d3695eebaf4de3539bd0a0bc6ee18c66af1ee183442f1758a0
|
| 3 |
-
size 15024
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/rng_state_1.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:1b38031f60d9e88601d369ef46bcdcf2b5b03f2cb4ba93853bcb2328df7ebb7c
|
| 3 |
-
size 15024
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/rng_state_2.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f58092375c93d237cd0e3149aecfbf83e2acdae46279e07a32920d01cb507e64
|
| 3 |
-
size 15024
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/rng_state_3.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:83cd4bbff9962da7ec6787fcea8d65df7096917f9a5902e249ba7aee8887fe5f
|
| 3 |
-
size 15024
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:03746929464b54010bdb23b85c112256bc4e1d2793521314f052727b3ea9e68f
|
| 3 |
-
size 1064
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/special_tokens_map.json
DELETED
|
@@ -1,17 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": {
|
| 3 |
-
"content": "<|begin_of_text|>",
|
| 4 |
-
"lstrip": false,
|
| 5 |
-
"normalized": false,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "<|eot_id|>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"pad_token": "<|eot_id|>"
|
| 17 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
-
size 17209920
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/tokenizer_config.json
DELETED
|
@@ -1,2064 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"added_tokens_decoder": {
|
| 3 |
-
"128000": {
|
| 4 |
-
"content": "<|begin_of_text|>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"128001": {
|
| 12 |
-
"content": "<|end_of_text|>",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"128002": {
|
| 20 |
-
"content": "<|reserved_special_token_0|>",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"128003": {
|
| 28 |
-
"content": "<|reserved_special_token_1|>",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"128004": {
|
| 36 |
-
"content": "<|finetune_right_pad_id|>",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
},
|
| 43 |
-
"128005": {
|
| 44 |
-
"content": "<|reserved_special_token_2|>",
|
| 45 |
-
"lstrip": false,
|
| 46 |
-
"normalized": false,
|
| 47 |
-
"rstrip": false,
|
| 48 |
-
"single_word": false,
|
| 49 |
-
"special": true
|
| 50 |
-
},
|
| 51 |
-
"128006": {
|
| 52 |
-
"content": "<|start_header_id|>",
|
| 53 |
-
"lstrip": false,
|
| 54 |
-
"normalized": false,
|
| 55 |
-
"rstrip": false,
|
| 56 |
-
"single_word": false,
|
| 57 |
-
"special": true
|
| 58 |
-
},
|
| 59 |
-
"128007": {
|
| 60 |
-
"content": "<|end_header_id|>",
|
| 61 |
-
"lstrip": false,
|
| 62 |
-
"normalized": false,
|
| 63 |
-
"rstrip": false,
|
| 64 |
-
"single_word": false,
|
| 65 |
-
"special": true
|
| 66 |
-
},
|
| 67 |
-
"128008": {
|
| 68 |
-
"content": "<|eom_id|>",
|
| 69 |
-
"lstrip": false,
|
| 70 |
-
"normalized": false,
|
| 71 |
-
"rstrip": false,
|
| 72 |
-
"single_word": false,
|
| 73 |
-
"special": true
|
| 74 |
-
},
|
| 75 |
-
"128009": {
|
| 76 |
-
"content": "<|eot_id|>",
|
| 77 |
-
"lstrip": false,
|
| 78 |
-
"normalized": false,
|
| 79 |
-
"rstrip": false,
|
| 80 |
-
"single_word": false,
|
| 81 |
-
"special": true
|
| 82 |
-
},
|
| 83 |
-
"128010": {
|
| 84 |
-
"content": "<|python_tag|>",
|
| 85 |
-
"lstrip": false,
|
| 86 |
-
"normalized": false,
|
| 87 |
-
"rstrip": false,
|
| 88 |
-
"single_word": false,
|
| 89 |
-
"special": true
|
| 90 |
-
},
|
| 91 |
-
"128011": {
|
| 92 |
-
"content": "<|reserved_special_token_3|>",
|
| 93 |
-
"lstrip": false,
|
| 94 |
-
"normalized": false,
|
| 95 |
-
"rstrip": false,
|
| 96 |
-
"single_word": false,
|
| 97 |
-
"special": true
|
| 98 |
-
},
|
| 99 |
-
"128012": {
|
| 100 |
-
"content": "<|reserved_special_token_4|>",
|
| 101 |
-
"lstrip": false,
|
| 102 |
-
"normalized": false,
|
| 103 |
-
"rstrip": false,
|
| 104 |
-
"single_word": false,
|
| 105 |
-
"special": true
|
| 106 |
-
},
|
| 107 |
-
"128013": {
|
| 108 |
-
"content": "<|reserved_special_token_5|>",
|
| 109 |
-
"lstrip": false,
|
| 110 |
-
"normalized": false,
|
| 111 |
-
"rstrip": false,
|
| 112 |
-
"single_word": false,
|
| 113 |
-
"special": true
|
| 114 |
-
},
|
| 115 |
-
"128014": {
|
| 116 |
-
"content": "<|reserved_special_token_6|>",
|
| 117 |
-
"lstrip": false,
|
| 118 |
-
"normalized": false,
|
| 119 |
-
"rstrip": false,
|
| 120 |
-
"single_word": false,
|
| 121 |
-
"special": true
|
| 122 |
-
},
|
| 123 |
-
"128015": {
|
| 124 |
-
"content": "<|reserved_special_token_7|>",
|
| 125 |
-
"lstrip": false,
|
| 126 |
-
"normalized": false,
|
| 127 |
-
"rstrip": false,
|
| 128 |
-
"single_word": false,
|
| 129 |
-
"special": true
|
| 130 |
-
},
|
| 131 |
-
"128016": {
|
| 132 |
-
"content": "<|reserved_special_token_8|>",
|
| 133 |
-
"lstrip": false,
|
| 134 |
-
"normalized": false,
|
| 135 |
-
"rstrip": false,
|
| 136 |
-
"single_word": false,
|
| 137 |
-
"special": true
|
| 138 |
-
},
|
| 139 |
-
"128017": {
|
| 140 |
-
"content": "<|reserved_special_token_9|>",
|
| 141 |
-
"lstrip": false,
|
| 142 |
-
"normalized": false,
|
| 143 |
-
"rstrip": false,
|
| 144 |
-
"single_word": false,
|
| 145 |
-
"special": true
|
| 146 |
-
},
|
| 147 |
-
"128018": {
|
| 148 |
-
"content": "<|reserved_special_token_10|>",
|
| 149 |
-
"lstrip": false,
|
| 150 |
-
"normalized": false,
|
| 151 |
-
"rstrip": false,
|
| 152 |
-
"single_word": false,
|
| 153 |
-
"special": true
|
| 154 |
-
},
|
| 155 |
-
"128019": {
|
| 156 |
-
"content": "<|reserved_special_token_11|>",
|
| 157 |
-
"lstrip": false,
|
| 158 |
-
"normalized": false,
|
| 159 |
-
"rstrip": false,
|
| 160 |
-
"single_word": false,
|
| 161 |
-
"special": true
|
| 162 |
-
},
|
| 163 |
-
"128020": {
|
| 164 |
-
"content": "<|reserved_special_token_12|>",
|
| 165 |
-
"lstrip": false,
|
| 166 |
-
"normalized": false,
|
| 167 |
-
"rstrip": false,
|
| 168 |
-
"single_word": false,
|
| 169 |
-
"special": true
|
| 170 |
-
},
|
| 171 |
-
"128021": {
|
| 172 |
-
"content": "<|reserved_special_token_13|>",
|
| 173 |
-
"lstrip": false,
|
| 174 |
-
"normalized": false,
|
| 175 |
-
"rstrip": false,
|
| 176 |
-
"single_word": false,
|
| 177 |
-
"special": true
|
| 178 |
-
},
|
| 179 |
-
"128022": {
|
| 180 |
-
"content": "<|reserved_special_token_14|>",
|
| 181 |
-
"lstrip": false,
|
| 182 |
-
"normalized": false,
|
| 183 |
-
"rstrip": false,
|
| 184 |
-
"single_word": false,
|
| 185 |
-
"special": true
|
| 186 |
-
},
|
| 187 |
-
"128023": {
|
| 188 |
-
"content": "<|reserved_special_token_15|>",
|
| 189 |
-
"lstrip": false,
|
| 190 |
-
"normalized": false,
|
| 191 |
-
"rstrip": false,
|
| 192 |
-
"single_word": false,
|
| 193 |
-
"special": true
|
| 194 |
-
},
|
| 195 |
-
"128024": {
|
| 196 |
-
"content": "<|reserved_special_token_16|>",
|
| 197 |
-
"lstrip": false,
|
| 198 |
-
"normalized": false,
|
| 199 |
-
"rstrip": false,
|
| 200 |
-
"single_word": false,
|
| 201 |
-
"special": true
|
| 202 |
-
},
|
| 203 |
-
"128025": {
|
| 204 |
-
"content": "<|reserved_special_token_17|>",
|
| 205 |
-
"lstrip": false,
|
| 206 |
-
"normalized": false,
|
| 207 |
-
"rstrip": false,
|
| 208 |
-
"single_word": false,
|
| 209 |
-
"special": true
|
| 210 |
-
},
|
| 211 |
-
"128026": {
|
| 212 |
-
"content": "<|reserved_special_token_18|>",
|
| 213 |
-
"lstrip": false,
|
| 214 |
-
"normalized": false,
|
| 215 |
-
"rstrip": false,
|
| 216 |
-
"single_word": false,
|
| 217 |
-
"special": true
|
| 218 |
-
},
|
| 219 |
-
"128027": {
|
| 220 |
-
"content": "<|reserved_special_token_19|>",
|
| 221 |
-
"lstrip": false,
|
| 222 |
-
"normalized": false,
|
| 223 |
-
"rstrip": false,
|
| 224 |
-
"single_word": false,
|
| 225 |
-
"special": true
|
| 226 |
-
},
|
| 227 |
-
"128028": {
|
| 228 |
-
"content": "<|reserved_special_token_20|>",
|
| 229 |
-
"lstrip": false,
|
| 230 |
-
"normalized": false,
|
| 231 |
-
"rstrip": false,
|
| 232 |
-
"single_word": false,
|
| 233 |
-
"special": true
|
| 234 |
-
},
|
| 235 |
-
"128029": {
|
| 236 |
-
"content": "<|reserved_special_token_21|>",
|
| 237 |
-
"lstrip": false,
|
| 238 |
-
"normalized": false,
|
| 239 |
-
"rstrip": false,
|
| 240 |
-
"single_word": false,
|
| 241 |
-
"special": true
|
| 242 |
-
},
|
| 243 |
-
"128030": {
|
| 244 |
-
"content": "<|reserved_special_token_22|>",
|
| 245 |
-
"lstrip": false,
|
| 246 |
-
"normalized": false,
|
| 247 |
-
"rstrip": false,
|
| 248 |
-
"single_word": false,
|
| 249 |
-
"special": true
|
| 250 |
-
},
|
| 251 |
-
"128031": {
|
| 252 |
-
"content": "<|reserved_special_token_23|>",
|
| 253 |
-
"lstrip": false,
|
| 254 |
-
"normalized": false,
|
| 255 |
-
"rstrip": false,
|
| 256 |
-
"single_word": false,
|
| 257 |
-
"special": true
|
| 258 |
-
},
|
| 259 |
-
"128032": {
|
| 260 |
-
"content": "<|reserved_special_token_24|>",
|
| 261 |
-
"lstrip": false,
|
| 262 |
-
"normalized": false,
|
| 263 |
-
"rstrip": false,
|
| 264 |
-
"single_word": false,
|
| 265 |
-
"special": true
|
| 266 |
-
},
|
| 267 |
-
"128033": {
|
| 268 |
-
"content": "<|reserved_special_token_25|>",
|
| 269 |
-
"lstrip": false,
|
| 270 |
-
"normalized": false,
|
| 271 |
-
"rstrip": false,
|
| 272 |
-
"single_word": false,
|
| 273 |
-
"special": true
|
| 274 |
-
},
|
| 275 |
-
"128034": {
|
| 276 |
-
"content": "<|reserved_special_token_26|>",
|
| 277 |
-
"lstrip": false,
|
| 278 |
-
"normalized": false,
|
| 279 |
-
"rstrip": false,
|
| 280 |
-
"single_word": false,
|
| 281 |
-
"special": true
|
| 282 |
-
},
|
| 283 |
-
"128035": {
|
| 284 |
-
"content": "<|reserved_special_token_27|>",
|
| 285 |
-
"lstrip": false,
|
| 286 |
-
"normalized": false,
|
| 287 |
-
"rstrip": false,
|
| 288 |
-
"single_word": false,
|
| 289 |
-
"special": true
|
| 290 |
-
},
|
| 291 |
-
"128036": {
|
| 292 |
-
"content": "<|reserved_special_token_28|>",
|
| 293 |
-
"lstrip": false,
|
| 294 |
-
"normalized": false,
|
| 295 |
-
"rstrip": false,
|
| 296 |
-
"single_word": false,
|
| 297 |
-
"special": true
|
| 298 |
-
},
|
| 299 |
-
"128037": {
|
| 300 |
-
"content": "<|reserved_special_token_29|>",
|
| 301 |
-
"lstrip": false,
|
| 302 |
-
"normalized": false,
|
| 303 |
-
"rstrip": false,
|
| 304 |
-
"single_word": false,
|
| 305 |
-
"special": true
|
| 306 |
-
},
|
| 307 |
-
"128038": {
|
| 308 |
-
"content": "<|reserved_special_token_30|>",
|
| 309 |
-
"lstrip": false,
|
| 310 |
-
"normalized": false,
|
| 311 |
-
"rstrip": false,
|
| 312 |
-
"single_word": false,
|
| 313 |
-
"special": true
|
| 314 |
-
},
|
| 315 |
-
"128039": {
|
| 316 |
-
"content": "<|reserved_special_token_31|>",
|
| 317 |
-
"lstrip": false,
|
| 318 |
-
"normalized": false,
|
| 319 |
-
"rstrip": false,
|
| 320 |
-
"single_word": false,
|
| 321 |
-
"special": true
|
| 322 |
-
},
|
| 323 |
-
"128040": {
|
| 324 |
-
"content": "<|reserved_special_token_32|>",
|
| 325 |
-
"lstrip": false,
|
| 326 |
-
"normalized": false,
|
| 327 |
-
"rstrip": false,
|
| 328 |
-
"single_word": false,
|
| 329 |
-
"special": true
|
| 330 |
-
},
|
| 331 |
-
"128041": {
|
| 332 |
-
"content": "<|reserved_special_token_33|>",
|
| 333 |
-
"lstrip": false,
|
| 334 |
-
"normalized": false,
|
| 335 |
-
"rstrip": false,
|
| 336 |
-
"single_word": false,
|
| 337 |
-
"special": true
|
| 338 |
-
},
|
| 339 |
-
"128042": {
|
| 340 |
-
"content": "<|reserved_special_token_34|>",
|
| 341 |
-
"lstrip": false,
|
| 342 |
-
"normalized": false,
|
| 343 |
-
"rstrip": false,
|
| 344 |
-
"single_word": false,
|
| 345 |
-
"special": true
|
| 346 |
-
},
|
| 347 |
-
"128043": {
|
| 348 |
-
"content": "<|reserved_special_token_35|>",
|
| 349 |
-
"lstrip": false,
|
| 350 |
-
"normalized": false,
|
| 351 |
-
"rstrip": false,
|
| 352 |
-
"single_word": false,
|
| 353 |
-
"special": true
|
| 354 |
-
},
|
| 355 |
-
"128044": {
|
| 356 |
-
"content": "<|reserved_special_token_36|>",
|
| 357 |
-
"lstrip": false,
|
| 358 |
-
"normalized": false,
|
| 359 |
-
"rstrip": false,
|
| 360 |
-
"single_word": false,
|
| 361 |
-
"special": true
|
| 362 |
-
},
|
| 363 |
-
"128045": {
|
| 364 |
-
"content": "<|reserved_special_token_37|>",
|
| 365 |
-
"lstrip": false,
|
| 366 |
-
"normalized": false,
|
| 367 |
-
"rstrip": false,
|
| 368 |
-
"single_word": false,
|
| 369 |
-
"special": true
|
| 370 |
-
},
|
| 371 |
-
"128046": {
|
| 372 |
-
"content": "<|reserved_special_token_38|>",
|
| 373 |
-
"lstrip": false,
|
| 374 |
-
"normalized": false,
|
| 375 |
-
"rstrip": false,
|
| 376 |
-
"single_word": false,
|
| 377 |
-
"special": true
|
| 378 |
-
},
|
| 379 |
-
"128047": {
|
| 380 |
-
"content": "<|reserved_special_token_39|>",
|
| 381 |
-
"lstrip": false,
|
| 382 |
-
"normalized": false,
|
| 383 |
-
"rstrip": false,
|
| 384 |
-
"single_word": false,
|
| 385 |
-
"special": true
|
| 386 |
-
},
|
| 387 |
-
"128048": {
|
| 388 |
-
"content": "<|reserved_special_token_40|>",
|
| 389 |
-
"lstrip": false,
|
| 390 |
-
"normalized": false,
|
| 391 |
-
"rstrip": false,
|
| 392 |
-
"single_word": false,
|
| 393 |
-
"special": true
|
| 394 |
-
},
|
| 395 |
-
"128049": {
|
| 396 |
-
"content": "<|reserved_special_token_41|>",
|
| 397 |
-
"lstrip": false,
|
| 398 |
-
"normalized": false,
|
| 399 |
-
"rstrip": false,
|
| 400 |
-
"single_word": false,
|
| 401 |
-
"special": true
|
| 402 |
-
},
|
| 403 |
-
"128050": {
|
| 404 |
-
"content": "<|reserved_special_token_42|>",
|
| 405 |
-
"lstrip": false,
|
| 406 |
-
"normalized": false,
|
| 407 |
-
"rstrip": false,
|
| 408 |
-
"single_word": false,
|
| 409 |
-
"special": true
|
| 410 |
-
},
|
| 411 |
-
"128051": {
|
| 412 |
-
"content": "<|reserved_special_token_43|>",
|
| 413 |
-
"lstrip": false,
|
| 414 |
-
"normalized": false,
|
| 415 |
-
"rstrip": false,
|
| 416 |
-
"single_word": false,
|
| 417 |
-
"special": true
|
| 418 |
-
},
|
| 419 |
-
"128052": {
|
| 420 |
-
"content": "<|reserved_special_token_44|>",
|
| 421 |
-
"lstrip": false,
|
| 422 |
-
"normalized": false,
|
| 423 |
-
"rstrip": false,
|
| 424 |
-
"single_word": false,
|
| 425 |
-
"special": true
|
| 426 |
-
},
|
| 427 |
-
"128053": {
|
| 428 |
-
"content": "<|reserved_special_token_45|>",
|
| 429 |
-
"lstrip": false,
|
| 430 |
-
"normalized": false,
|
| 431 |
-
"rstrip": false,
|
| 432 |
-
"single_word": false,
|
| 433 |
-
"special": true
|
| 434 |
-
},
|
| 435 |
-
"128054": {
|
| 436 |
-
"content": "<|reserved_special_token_46|>",
|
| 437 |
-
"lstrip": false,
|
| 438 |
-
"normalized": false,
|
| 439 |
-
"rstrip": false,
|
| 440 |
-
"single_word": false,
|
| 441 |
-
"special": true
|
| 442 |
-
},
|
| 443 |
-
"128055": {
|
| 444 |
-
"content": "<|reserved_special_token_47|>",
|
| 445 |
-
"lstrip": false,
|
| 446 |
-
"normalized": false,
|
| 447 |
-
"rstrip": false,
|
| 448 |
-
"single_word": false,
|
| 449 |
-
"special": true
|
| 450 |
-
},
|
| 451 |
-
"128056": {
|
| 452 |
-
"content": "<|reserved_special_token_48|>",
|
| 453 |
-
"lstrip": false,
|
| 454 |
-
"normalized": false,
|
| 455 |
-
"rstrip": false,
|
| 456 |
-
"single_word": false,
|
| 457 |
-
"special": true
|
| 458 |
-
},
|
| 459 |
-
"128057": {
|
| 460 |
-
"content": "<|reserved_special_token_49|>",
|
| 461 |
-
"lstrip": false,
|
| 462 |
-
"normalized": false,
|
| 463 |
-
"rstrip": false,
|
| 464 |
-
"single_word": false,
|
| 465 |
-
"special": true
|
| 466 |
-
},
|
| 467 |
-
"128058": {
|
| 468 |
-
"content": "<|reserved_special_token_50|>",
|
| 469 |
-
"lstrip": false,
|
| 470 |
-
"normalized": false,
|
| 471 |
-
"rstrip": false,
|
| 472 |
-
"single_word": false,
|
| 473 |
-
"special": true
|
| 474 |
-
},
|
| 475 |
-
"128059": {
|
| 476 |
-
"content": "<|reserved_special_token_51|>",
|
| 477 |
-
"lstrip": false,
|
| 478 |
-
"normalized": false,
|
| 479 |
-
"rstrip": false,
|
| 480 |
-
"single_word": false,
|
| 481 |
-
"special": true
|
| 482 |
-
},
|
| 483 |
-
"128060": {
|
| 484 |
-
"content": "<|reserved_special_token_52|>",
|
| 485 |
-
"lstrip": false,
|
| 486 |
-
"normalized": false,
|
| 487 |
-
"rstrip": false,
|
| 488 |
-
"single_word": false,
|
| 489 |
-
"special": true
|
| 490 |
-
},
|
| 491 |
-
"128061": {
|
| 492 |
-
"content": "<|reserved_special_token_53|>",
|
| 493 |
-
"lstrip": false,
|
| 494 |
-
"normalized": false,
|
| 495 |
-
"rstrip": false,
|
| 496 |
-
"single_word": false,
|
| 497 |
-
"special": true
|
| 498 |
-
},
|
| 499 |
-
"128062": {
|
| 500 |
-
"content": "<|reserved_special_token_54|>",
|
| 501 |
-
"lstrip": false,
|
| 502 |
-
"normalized": false,
|
| 503 |
-
"rstrip": false,
|
| 504 |
-
"single_word": false,
|
| 505 |
-
"special": true
|
| 506 |
-
},
|
| 507 |
-
"128063": {
|
| 508 |
-
"content": "<|reserved_special_token_55|>",
|
| 509 |
-
"lstrip": false,
|
| 510 |
-
"normalized": false,
|
| 511 |
-
"rstrip": false,
|
| 512 |
-
"single_word": false,
|
| 513 |
-
"special": true
|
| 514 |
-
},
|
| 515 |
-
"128064": {
|
| 516 |
-
"content": "<|reserved_special_token_56|>",
|
| 517 |
-
"lstrip": false,
|
| 518 |
-
"normalized": false,
|
| 519 |
-
"rstrip": false,
|
| 520 |
-
"single_word": false,
|
| 521 |
-
"special": true
|
| 522 |
-
},
|
| 523 |
-
"128065": {
|
| 524 |
-
"content": "<|reserved_special_token_57|>",
|
| 525 |
-
"lstrip": false,
|
| 526 |
-
"normalized": false,
|
| 527 |
-
"rstrip": false,
|
| 528 |
-
"single_word": false,
|
| 529 |
-
"special": true
|
| 530 |
-
},
|
| 531 |
-
"128066": {
|
| 532 |
-
"content": "<|reserved_special_token_58|>",
|
| 533 |
-
"lstrip": false,
|
| 534 |
-
"normalized": false,
|
| 535 |
-
"rstrip": false,
|
| 536 |
-
"single_word": false,
|
| 537 |
-
"special": true
|
| 538 |
-
},
|
| 539 |
-
"128067": {
|
| 540 |
-
"content": "<|reserved_special_token_59|>",
|
| 541 |
-
"lstrip": false,
|
| 542 |
-
"normalized": false,
|
| 543 |
-
"rstrip": false,
|
| 544 |
-
"single_word": false,
|
| 545 |
-
"special": true
|
| 546 |
-
},
|
| 547 |
-
"128068": {
|
| 548 |
-
"content": "<|reserved_special_token_60|>",
|
| 549 |
-
"lstrip": false,
|
| 550 |
-
"normalized": false,
|
| 551 |
-
"rstrip": false,
|
| 552 |
-
"single_word": false,
|
| 553 |
-
"special": true
|
| 554 |
-
},
|
| 555 |
-
"128069": {
|
| 556 |
-
"content": "<|reserved_special_token_61|>",
|
| 557 |
-
"lstrip": false,
|
| 558 |
-
"normalized": false,
|
| 559 |
-
"rstrip": false,
|
| 560 |
-
"single_word": false,
|
| 561 |
-
"special": true
|
| 562 |
-
},
|
| 563 |
-
"128070": {
|
| 564 |
-
"content": "<|reserved_special_token_62|>",
|
| 565 |
-
"lstrip": false,
|
| 566 |
-
"normalized": false,
|
| 567 |
-
"rstrip": false,
|
| 568 |
-
"single_word": false,
|
| 569 |
-
"special": true
|
| 570 |
-
},
|
| 571 |
-
"128071": {
|
| 572 |
-
"content": "<|reserved_special_token_63|>",
|
| 573 |
-
"lstrip": false,
|
| 574 |
-
"normalized": false,
|
| 575 |
-
"rstrip": false,
|
| 576 |
-
"single_word": false,
|
| 577 |
-
"special": true
|
| 578 |
-
},
|
| 579 |
-
"128072": {
|
| 580 |
-
"content": "<|reserved_special_token_64|>",
|
| 581 |
-
"lstrip": false,
|
| 582 |
-
"normalized": false,
|
| 583 |
-
"rstrip": false,
|
| 584 |
-
"single_word": false,
|
| 585 |
-
"special": true
|
| 586 |
-
},
|
| 587 |
-
"128073": {
|
| 588 |
-
"content": "<|reserved_special_token_65|>",
|
| 589 |
-
"lstrip": false,
|
| 590 |
-
"normalized": false,
|
| 591 |
-
"rstrip": false,
|
| 592 |
-
"single_word": false,
|
| 593 |
-
"special": true
|
| 594 |
-
},
|
| 595 |
-
"128074": {
|
| 596 |
-
"content": "<|reserved_special_token_66|>",
|
| 597 |
-
"lstrip": false,
|
| 598 |
-
"normalized": false,
|
| 599 |
-
"rstrip": false,
|
| 600 |
-
"single_word": false,
|
| 601 |
-
"special": true
|
| 602 |
-
},
|
| 603 |
-
"128075": {
|
| 604 |
-
"content": "<|reserved_special_token_67|>",
|
| 605 |
-
"lstrip": false,
|
| 606 |
-
"normalized": false,
|
| 607 |
-
"rstrip": false,
|
| 608 |
-
"single_word": false,
|
| 609 |
-
"special": true
|
| 610 |
-
},
|
| 611 |
-
"128076": {
|
| 612 |
-
"content": "<|reserved_special_token_68|>",
|
| 613 |
-
"lstrip": false,
|
| 614 |
-
"normalized": false,
|
| 615 |
-
"rstrip": false,
|
| 616 |
-
"single_word": false,
|
| 617 |
-
"special": true
|
| 618 |
-
},
|
| 619 |
-
"128077": {
|
| 620 |
-
"content": "<|reserved_special_token_69|>",
|
| 621 |
-
"lstrip": false,
|
| 622 |
-
"normalized": false,
|
| 623 |
-
"rstrip": false,
|
| 624 |
-
"single_word": false,
|
| 625 |
-
"special": true
|
| 626 |
-
},
|
| 627 |
-
"128078": {
|
| 628 |
-
"content": "<|reserved_special_token_70|>",
|
| 629 |
-
"lstrip": false,
|
| 630 |
-
"normalized": false,
|
| 631 |
-
"rstrip": false,
|
| 632 |
-
"single_word": false,
|
| 633 |
-
"special": true
|
| 634 |
-
},
|
| 635 |
-
"128079": {
|
| 636 |
-
"content": "<|reserved_special_token_71|>",
|
| 637 |
-
"lstrip": false,
|
| 638 |
-
"normalized": false,
|
| 639 |
-
"rstrip": false,
|
| 640 |
-
"single_word": false,
|
| 641 |
-
"special": true
|
| 642 |
-
},
|
| 643 |
-
"128080": {
|
| 644 |
-
"content": "<|reserved_special_token_72|>",
|
| 645 |
-
"lstrip": false,
|
| 646 |
-
"normalized": false,
|
| 647 |
-
"rstrip": false,
|
| 648 |
-
"single_word": false,
|
| 649 |
-
"special": true
|
| 650 |
-
},
|
| 651 |
-
"128081": {
|
| 652 |
-
"content": "<|reserved_special_token_73|>",
|
| 653 |
-
"lstrip": false,
|
| 654 |
-
"normalized": false,
|
| 655 |
-
"rstrip": false,
|
| 656 |
-
"single_word": false,
|
| 657 |
-
"special": true
|
| 658 |
-
},
|
| 659 |
-
"128082": {
|
| 660 |
-
"content": "<|reserved_special_token_74|>",
|
| 661 |
-
"lstrip": false,
|
| 662 |
-
"normalized": false,
|
| 663 |
-
"rstrip": false,
|
| 664 |
-
"single_word": false,
|
| 665 |
-
"special": true
|
| 666 |
-
},
|
| 667 |
-
"128083": {
|
| 668 |
-
"content": "<|reserved_special_token_75|>",
|
| 669 |
-
"lstrip": false,
|
| 670 |
-
"normalized": false,
|
| 671 |
-
"rstrip": false,
|
| 672 |
-
"single_word": false,
|
| 673 |
-
"special": true
|
| 674 |
-
},
|
| 675 |
-
"128084": {
|
| 676 |
-
"content": "<|reserved_special_token_76|>",
|
| 677 |
-
"lstrip": false,
|
| 678 |
-
"normalized": false,
|
| 679 |
-
"rstrip": false,
|
| 680 |
-
"single_word": false,
|
| 681 |
-
"special": true
|
| 682 |
-
},
|
| 683 |
-
"128085": {
|
| 684 |
-
"content": "<|reserved_special_token_77|>",
|
| 685 |
-
"lstrip": false,
|
| 686 |
-
"normalized": false,
|
| 687 |
-
"rstrip": false,
|
| 688 |
-
"single_word": false,
|
| 689 |
-
"special": true
|
| 690 |
-
},
|
| 691 |
-
"128086": {
|
| 692 |
-
"content": "<|reserved_special_token_78|>",
|
| 693 |
-
"lstrip": false,
|
| 694 |
-
"normalized": false,
|
| 695 |
-
"rstrip": false,
|
| 696 |
-
"single_word": false,
|
| 697 |
-
"special": true
|
| 698 |
-
},
|
| 699 |
-
"128087": {
|
| 700 |
-
"content": "<|reserved_special_token_79|>",
|
| 701 |
-
"lstrip": false,
|
| 702 |
-
"normalized": false,
|
| 703 |
-
"rstrip": false,
|
| 704 |
-
"single_word": false,
|
| 705 |
-
"special": true
|
| 706 |
-
},
|
| 707 |
-
"128088": {
|
| 708 |
-
"content": "<|reserved_special_token_80|>",
|
| 709 |
-
"lstrip": false,
|
| 710 |
-
"normalized": false,
|
| 711 |
-
"rstrip": false,
|
| 712 |
-
"single_word": false,
|
| 713 |
-
"special": true
|
| 714 |
-
},
|
| 715 |
-
"128089": {
|
| 716 |
-
"content": "<|reserved_special_token_81|>",
|
| 717 |
-
"lstrip": false,
|
| 718 |
-
"normalized": false,
|
| 719 |
-
"rstrip": false,
|
| 720 |
-
"single_word": false,
|
| 721 |
-
"special": true
|
| 722 |
-
},
|
| 723 |
-
"128090": {
|
| 724 |
-
"content": "<|reserved_special_token_82|>",
|
| 725 |
-
"lstrip": false,
|
| 726 |
-
"normalized": false,
|
| 727 |
-
"rstrip": false,
|
| 728 |
-
"single_word": false,
|
| 729 |
-
"special": true
|
| 730 |
-
},
|
| 731 |
-
"128091": {
|
| 732 |
-
"content": "<|reserved_special_token_83|>",
|
| 733 |
-
"lstrip": false,
|
| 734 |
-
"normalized": false,
|
| 735 |
-
"rstrip": false,
|
| 736 |
-
"single_word": false,
|
| 737 |
-
"special": true
|
| 738 |
-
},
|
| 739 |
-
"128092": {
|
| 740 |
-
"content": "<|reserved_special_token_84|>",
|
| 741 |
-
"lstrip": false,
|
| 742 |
-
"normalized": false,
|
| 743 |
-
"rstrip": false,
|
| 744 |
-
"single_word": false,
|
| 745 |
-
"special": true
|
| 746 |
-
},
|
| 747 |
-
"128093": {
|
| 748 |
-
"content": "<|reserved_special_token_85|>",
|
| 749 |
-
"lstrip": false,
|
| 750 |
-
"normalized": false,
|
| 751 |
-
"rstrip": false,
|
| 752 |
-
"single_word": false,
|
| 753 |
-
"special": true
|
| 754 |
-
},
|
| 755 |
-
"128094": {
|
| 756 |
-
"content": "<|reserved_special_token_86|>",
|
| 757 |
-
"lstrip": false,
|
| 758 |
-
"normalized": false,
|
| 759 |
-
"rstrip": false,
|
| 760 |
-
"single_word": false,
|
| 761 |
-
"special": true
|
| 762 |
-
},
|
| 763 |
-
"128095": {
|
| 764 |
-
"content": "<|reserved_special_token_87|>",
|
| 765 |
-
"lstrip": false,
|
| 766 |
-
"normalized": false,
|
| 767 |
-
"rstrip": false,
|
| 768 |
-
"single_word": false,
|
| 769 |
-
"special": true
|
| 770 |
-
},
|
| 771 |
-
"128096": {
|
| 772 |
-
"content": "<|reserved_special_token_88|>",
|
| 773 |
-
"lstrip": false,
|
| 774 |
-
"normalized": false,
|
| 775 |
-
"rstrip": false,
|
| 776 |
-
"single_word": false,
|
| 777 |
-
"special": true
|
| 778 |
-
},
|
| 779 |
-
"128097": {
|
| 780 |
-
"content": "<|reserved_special_token_89|>",
|
| 781 |
-
"lstrip": false,
|
| 782 |
-
"normalized": false,
|
| 783 |
-
"rstrip": false,
|
| 784 |
-
"single_word": false,
|
| 785 |
-
"special": true
|
| 786 |
-
},
|
| 787 |
-
"128098": {
|
| 788 |
-
"content": "<|reserved_special_token_90|>",
|
| 789 |
-
"lstrip": false,
|
| 790 |
-
"normalized": false,
|
| 791 |
-
"rstrip": false,
|
| 792 |
-
"single_word": false,
|
| 793 |
-
"special": true
|
| 794 |
-
},
|
| 795 |
-
"128099": {
|
| 796 |
-
"content": "<|reserved_special_token_91|>",
|
| 797 |
-
"lstrip": false,
|
| 798 |
-
"normalized": false,
|
| 799 |
-
"rstrip": false,
|
| 800 |
-
"single_word": false,
|
| 801 |
-
"special": true
|
| 802 |
-
},
|
| 803 |
-
"128100": {
|
| 804 |
-
"content": "<|reserved_special_token_92|>",
|
| 805 |
-
"lstrip": false,
|
| 806 |
-
"normalized": false,
|
| 807 |
-
"rstrip": false,
|
| 808 |
-
"single_word": false,
|
| 809 |
-
"special": true
|
| 810 |
-
},
|
| 811 |
-
"128101": {
|
| 812 |
-
"content": "<|reserved_special_token_93|>",
|
| 813 |
-
"lstrip": false,
|
| 814 |
-
"normalized": false,
|
| 815 |
-
"rstrip": false,
|
| 816 |
-
"single_word": false,
|
| 817 |
-
"special": true
|
| 818 |
-
},
|
| 819 |
-
"128102": {
|
| 820 |
-
"content": "<|reserved_special_token_94|>",
|
| 821 |
-
"lstrip": false,
|
| 822 |
-
"normalized": false,
|
| 823 |
-
"rstrip": false,
|
| 824 |
-
"single_word": false,
|
| 825 |
-
"special": true
|
| 826 |
-
},
|
| 827 |
-
"128103": {
|
| 828 |
-
"content": "<|reserved_special_token_95|>",
|
| 829 |
-
"lstrip": false,
|
| 830 |
-
"normalized": false,
|
| 831 |
-
"rstrip": false,
|
| 832 |
-
"single_word": false,
|
| 833 |
-
"special": true
|
| 834 |
-
},
|
| 835 |
-
"128104": {
|
| 836 |
-
"content": "<|reserved_special_token_96|>",
|
| 837 |
-
"lstrip": false,
|
| 838 |
-
"normalized": false,
|
| 839 |
-
"rstrip": false,
|
| 840 |
-
"single_word": false,
|
| 841 |
-
"special": true
|
| 842 |
-
},
|
| 843 |
-
"128105": {
|
| 844 |
-
"content": "<|reserved_special_token_97|>",
|
| 845 |
-
"lstrip": false,
|
| 846 |
-
"normalized": false,
|
| 847 |
-
"rstrip": false,
|
| 848 |
-
"single_word": false,
|
| 849 |
-
"special": true
|
| 850 |
-
},
|
| 851 |
-
"128106": {
|
| 852 |
-
"content": "<|reserved_special_token_98|>",
|
| 853 |
-
"lstrip": false,
|
| 854 |
-
"normalized": false,
|
| 855 |
-
"rstrip": false,
|
| 856 |
-
"single_word": false,
|
| 857 |
-
"special": true
|
| 858 |
-
},
|
| 859 |
-
"128107": {
|
| 860 |
-
"content": "<|reserved_special_token_99|>",
|
| 861 |
-
"lstrip": false,
|
| 862 |
-
"normalized": false,
|
| 863 |
-
"rstrip": false,
|
| 864 |
-
"single_word": false,
|
| 865 |
-
"special": true
|
| 866 |
-
},
|
| 867 |
-
"128108": {
|
| 868 |
-
"content": "<|reserved_special_token_100|>",
|
| 869 |
-
"lstrip": false,
|
| 870 |
-
"normalized": false,
|
| 871 |
-
"rstrip": false,
|
| 872 |
-
"single_word": false,
|
| 873 |
-
"special": true
|
| 874 |
-
},
|
| 875 |
-
"128109": {
|
| 876 |
-
"content": "<|reserved_special_token_101|>",
|
| 877 |
-
"lstrip": false,
|
| 878 |
-
"normalized": false,
|
| 879 |
-
"rstrip": false,
|
| 880 |
-
"single_word": false,
|
| 881 |
-
"special": true
|
| 882 |
-
},
|
| 883 |
-
"128110": {
|
| 884 |
-
"content": "<|reserved_special_token_102|>",
|
| 885 |
-
"lstrip": false,
|
| 886 |
-
"normalized": false,
|
| 887 |
-
"rstrip": false,
|
| 888 |
-
"single_word": false,
|
| 889 |
-
"special": true
|
| 890 |
-
},
|
| 891 |
-
"128111": {
|
| 892 |
-
"content": "<|reserved_special_token_103|>",
|
| 893 |
-
"lstrip": false,
|
| 894 |
-
"normalized": false,
|
| 895 |
-
"rstrip": false,
|
| 896 |
-
"single_word": false,
|
| 897 |
-
"special": true
|
| 898 |
-
},
|
| 899 |
-
"128112": {
|
| 900 |
-
"content": "<|reserved_special_token_104|>",
|
| 901 |
-
"lstrip": false,
|
| 902 |
-
"normalized": false,
|
| 903 |
-
"rstrip": false,
|
| 904 |
-
"single_word": false,
|
| 905 |
-
"special": true
|
| 906 |
-
},
|
| 907 |
-
"128113": {
|
| 908 |
-
"content": "<|reserved_special_token_105|>",
|
| 909 |
-
"lstrip": false,
|
| 910 |
-
"normalized": false,
|
| 911 |
-
"rstrip": false,
|
| 912 |
-
"single_word": false,
|
| 913 |
-
"special": true
|
| 914 |
-
},
|
| 915 |
-
"128114": {
|
| 916 |
-
"content": "<|reserved_special_token_106|>",
|
| 917 |
-
"lstrip": false,
|
| 918 |
-
"normalized": false,
|
| 919 |
-
"rstrip": false,
|
| 920 |
-
"single_word": false,
|
| 921 |
-
"special": true
|
| 922 |
-
},
|
| 923 |
-
"128115": {
|
| 924 |
-
"content": "<|reserved_special_token_107|>",
|
| 925 |
-
"lstrip": false,
|
| 926 |
-
"normalized": false,
|
| 927 |
-
"rstrip": false,
|
| 928 |
-
"single_word": false,
|
| 929 |
-
"special": true
|
| 930 |
-
},
|
| 931 |
-
"128116": {
|
| 932 |
-
"content": "<|reserved_special_token_108|>",
|
| 933 |
-
"lstrip": false,
|
| 934 |
-
"normalized": false,
|
| 935 |
-
"rstrip": false,
|
| 936 |
-
"single_word": false,
|
| 937 |
-
"special": true
|
| 938 |
-
},
|
| 939 |
-
"128117": {
|
| 940 |
-
"content": "<|reserved_special_token_109|>",
|
| 941 |
-
"lstrip": false,
|
| 942 |
-
"normalized": false,
|
| 943 |
-
"rstrip": false,
|
| 944 |
-
"single_word": false,
|
| 945 |
-
"special": true
|
| 946 |
-
},
|
| 947 |
-
"128118": {
|
| 948 |
-
"content": "<|reserved_special_token_110|>",
|
| 949 |
-
"lstrip": false,
|
| 950 |
-
"normalized": false,
|
| 951 |
-
"rstrip": false,
|
| 952 |
-
"single_word": false,
|
| 953 |
-
"special": true
|
| 954 |
-
},
|
| 955 |
-
"128119": {
|
| 956 |
-
"content": "<|reserved_special_token_111|>",
|
| 957 |
-
"lstrip": false,
|
| 958 |
-
"normalized": false,
|
| 959 |
-
"rstrip": false,
|
| 960 |
-
"single_word": false,
|
| 961 |
-
"special": true
|
| 962 |
-
},
|
| 963 |
-
"128120": {
|
| 964 |
-
"content": "<|reserved_special_token_112|>",
|
| 965 |
-
"lstrip": false,
|
| 966 |
-
"normalized": false,
|
| 967 |
-
"rstrip": false,
|
| 968 |
-
"single_word": false,
|
| 969 |
-
"special": true
|
| 970 |
-
},
|
| 971 |
-
"128121": {
|
| 972 |
-
"content": "<|reserved_special_token_113|>",
|
| 973 |
-
"lstrip": false,
|
| 974 |
-
"normalized": false,
|
| 975 |
-
"rstrip": false,
|
| 976 |
-
"single_word": false,
|
| 977 |
-
"special": true
|
| 978 |
-
},
|
| 979 |
-
"128122": {
|
| 980 |
-
"content": "<|reserved_special_token_114|>",
|
| 981 |
-
"lstrip": false,
|
| 982 |
-
"normalized": false,
|
| 983 |
-
"rstrip": false,
|
| 984 |
-
"single_word": false,
|
| 985 |
-
"special": true
|
| 986 |
-
},
|
| 987 |
-
"128123": {
|
| 988 |
-
"content": "<|reserved_special_token_115|>",
|
| 989 |
-
"lstrip": false,
|
| 990 |
-
"normalized": false,
|
| 991 |
-
"rstrip": false,
|
| 992 |
-
"single_word": false,
|
| 993 |
-
"special": true
|
| 994 |
-
},
|
| 995 |
-
"128124": {
|
| 996 |
-
"content": "<|reserved_special_token_116|>",
|
| 997 |
-
"lstrip": false,
|
| 998 |
-
"normalized": false,
|
| 999 |
-
"rstrip": false,
|
| 1000 |
-
"single_word": false,
|
| 1001 |
-
"special": true
|
| 1002 |
-
},
|
| 1003 |
-
"128125": {
|
| 1004 |
-
"content": "<|reserved_special_token_117|>",
|
| 1005 |
-
"lstrip": false,
|
| 1006 |
-
"normalized": false,
|
| 1007 |
-
"rstrip": false,
|
| 1008 |
-
"single_word": false,
|
| 1009 |
-
"special": true
|
| 1010 |
-
},
|
| 1011 |
-
"128126": {
|
| 1012 |
-
"content": "<|reserved_special_token_118|>",
|
| 1013 |
-
"lstrip": false,
|
| 1014 |
-
"normalized": false,
|
| 1015 |
-
"rstrip": false,
|
| 1016 |
-
"single_word": false,
|
| 1017 |
-
"special": true
|
| 1018 |
-
},
|
| 1019 |
-
"128127": {
|
| 1020 |
-
"content": "<|reserved_special_token_119|>",
|
| 1021 |
-
"lstrip": false,
|
| 1022 |
-
"normalized": false,
|
| 1023 |
-
"rstrip": false,
|
| 1024 |
-
"single_word": false,
|
| 1025 |
-
"special": true
|
| 1026 |
-
},
|
| 1027 |
-
"128128": {
|
| 1028 |
-
"content": "<|reserved_special_token_120|>",
|
| 1029 |
-
"lstrip": false,
|
| 1030 |
-
"normalized": false,
|
| 1031 |
-
"rstrip": false,
|
| 1032 |
-
"single_word": false,
|
| 1033 |
-
"special": true
|
| 1034 |
-
},
|
| 1035 |
-
"128129": {
|
| 1036 |
-
"content": "<|reserved_special_token_121|>",
|
| 1037 |
-
"lstrip": false,
|
| 1038 |
-
"normalized": false,
|
| 1039 |
-
"rstrip": false,
|
| 1040 |
-
"single_word": false,
|
| 1041 |
-
"special": true
|
| 1042 |
-
},
|
| 1043 |
-
"128130": {
|
| 1044 |
-
"content": "<|reserved_special_token_122|>",
|
| 1045 |
-
"lstrip": false,
|
| 1046 |
-
"normalized": false,
|
| 1047 |
-
"rstrip": false,
|
| 1048 |
-
"single_word": false,
|
| 1049 |
-
"special": true
|
| 1050 |
-
},
|
| 1051 |
-
"128131": {
|
| 1052 |
-
"content": "<|reserved_special_token_123|>",
|
| 1053 |
-
"lstrip": false,
|
| 1054 |
-
"normalized": false,
|
| 1055 |
-
"rstrip": false,
|
| 1056 |
-
"single_word": false,
|
| 1057 |
-
"special": true
|
| 1058 |
-
},
|
| 1059 |
-
"128132": {
|
| 1060 |
-
"content": "<|reserved_special_token_124|>",
|
| 1061 |
-
"lstrip": false,
|
| 1062 |
-
"normalized": false,
|
| 1063 |
-
"rstrip": false,
|
| 1064 |
-
"single_word": false,
|
| 1065 |
-
"special": true
|
| 1066 |
-
},
|
| 1067 |
-
"128133": {
|
| 1068 |
-
"content": "<|reserved_special_token_125|>",
|
| 1069 |
-
"lstrip": false,
|
| 1070 |
-
"normalized": false,
|
| 1071 |
-
"rstrip": false,
|
| 1072 |
-
"single_word": false,
|
| 1073 |
-
"special": true
|
| 1074 |
-
},
|
| 1075 |
-
"128134": {
|
| 1076 |
-
"content": "<|reserved_special_token_126|>",
|
| 1077 |
-
"lstrip": false,
|
| 1078 |
-
"normalized": false,
|
| 1079 |
-
"rstrip": false,
|
| 1080 |
-
"single_word": false,
|
| 1081 |
-
"special": true
|
| 1082 |
-
},
|
| 1083 |
-
"128135": {
|
| 1084 |
-
"content": "<|reserved_special_token_127|>",
|
| 1085 |
-
"lstrip": false,
|
| 1086 |
-
"normalized": false,
|
| 1087 |
-
"rstrip": false,
|
| 1088 |
-
"single_word": false,
|
| 1089 |
-
"special": true
|
| 1090 |
-
},
|
| 1091 |
-
"128136": {
|
| 1092 |
-
"content": "<|reserved_special_token_128|>",
|
| 1093 |
-
"lstrip": false,
|
| 1094 |
-
"normalized": false,
|
| 1095 |
-
"rstrip": false,
|
| 1096 |
-
"single_word": false,
|
| 1097 |
-
"special": true
|
| 1098 |
-
},
|
| 1099 |
-
"128137": {
|
| 1100 |
-
"content": "<|reserved_special_token_129|>",
|
| 1101 |
-
"lstrip": false,
|
| 1102 |
-
"normalized": false,
|
| 1103 |
-
"rstrip": false,
|
| 1104 |
-
"single_word": false,
|
| 1105 |
-
"special": true
|
| 1106 |
-
},
|
| 1107 |
-
"128138": {
|
| 1108 |
-
"content": "<|reserved_special_token_130|>",
|
| 1109 |
-
"lstrip": false,
|
| 1110 |
-
"normalized": false,
|
| 1111 |
-
"rstrip": false,
|
| 1112 |
-
"single_word": false,
|
| 1113 |
-
"special": true
|
| 1114 |
-
},
|
| 1115 |
-
"128139": {
|
| 1116 |
-
"content": "<|reserved_special_token_131|>",
|
| 1117 |
-
"lstrip": false,
|
| 1118 |
-
"normalized": false,
|
| 1119 |
-
"rstrip": false,
|
| 1120 |
-
"single_word": false,
|
| 1121 |
-
"special": true
|
| 1122 |
-
},
|
| 1123 |
-
"128140": {
|
| 1124 |
-
"content": "<|reserved_special_token_132|>",
|
| 1125 |
-
"lstrip": false,
|
| 1126 |
-
"normalized": false,
|
| 1127 |
-
"rstrip": false,
|
| 1128 |
-
"single_word": false,
|
| 1129 |
-
"special": true
|
| 1130 |
-
},
|
| 1131 |
-
"128141": {
|
| 1132 |
-
"content": "<|reserved_special_token_133|>",
|
| 1133 |
-
"lstrip": false,
|
| 1134 |
-
"normalized": false,
|
| 1135 |
-
"rstrip": false,
|
| 1136 |
-
"single_word": false,
|
| 1137 |
-
"special": true
|
| 1138 |
-
},
|
| 1139 |
-
"128142": {
|
| 1140 |
-
"content": "<|reserved_special_token_134|>",
|
| 1141 |
-
"lstrip": false,
|
| 1142 |
-
"normalized": false,
|
| 1143 |
-
"rstrip": false,
|
| 1144 |
-
"single_word": false,
|
| 1145 |
-
"special": true
|
| 1146 |
-
},
|
| 1147 |
-
"128143": {
|
| 1148 |
-
"content": "<|reserved_special_token_135|>",
|
| 1149 |
-
"lstrip": false,
|
| 1150 |
-
"normalized": false,
|
| 1151 |
-
"rstrip": false,
|
| 1152 |
-
"single_word": false,
|
| 1153 |
-
"special": true
|
| 1154 |
-
},
|
| 1155 |
-
"128144": {
|
| 1156 |
-
"content": "<|reserved_special_token_136|>",
|
| 1157 |
-
"lstrip": false,
|
| 1158 |
-
"normalized": false,
|
| 1159 |
-
"rstrip": false,
|
| 1160 |
-
"single_word": false,
|
| 1161 |
-
"special": true
|
| 1162 |
-
},
|
| 1163 |
-
"128145": {
|
| 1164 |
-
"content": "<|reserved_special_token_137|>",
|
| 1165 |
-
"lstrip": false,
|
| 1166 |
-
"normalized": false,
|
| 1167 |
-
"rstrip": false,
|
| 1168 |
-
"single_word": false,
|
| 1169 |
-
"special": true
|
| 1170 |
-
},
|
| 1171 |
-
"128146": {
|
| 1172 |
-
"content": "<|reserved_special_token_138|>",
|
| 1173 |
-
"lstrip": false,
|
| 1174 |
-
"normalized": false,
|
| 1175 |
-
"rstrip": false,
|
| 1176 |
-
"single_word": false,
|
| 1177 |
-
"special": true
|
| 1178 |
-
},
|
| 1179 |
-
"128147": {
|
| 1180 |
-
"content": "<|reserved_special_token_139|>",
|
| 1181 |
-
"lstrip": false,
|
| 1182 |
-
"normalized": false,
|
| 1183 |
-
"rstrip": false,
|
| 1184 |
-
"single_word": false,
|
| 1185 |
-
"special": true
|
| 1186 |
-
},
|
| 1187 |
-
"128148": {
|
| 1188 |
-
"content": "<|reserved_special_token_140|>",
|
| 1189 |
-
"lstrip": false,
|
| 1190 |
-
"normalized": false,
|
| 1191 |
-
"rstrip": false,
|
| 1192 |
-
"single_word": false,
|
| 1193 |
-
"special": true
|
| 1194 |
-
},
|
| 1195 |
-
"128149": {
|
| 1196 |
-
"content": "<|reserved_special_token_141|>",
|
| 1197 |
-
"lstrip": false,
|
| 1198 |
-
"normalized": false,
|
| 1199 |
-
"rstrip": false,
|
| 1200 |
-
"single_word": false,
|
| 1201 |
-
"special": true
|
| 1202 |
-
},
|
| 1203 |
-
"128150": {
|
| 1204 |
-
"content": "<|reserved_special_token_142|>",
|
| 1205 |
-
"lstrip": false,
|
| 1206 |
-
"normalized": false,
|
| 1207 |
-
"rstrip": false,
|
| 1208 |
-
"single_word": false,
|
| 1209 |
-
"special": true
|
| 1210 |
-
},
|
| 1211 |
-
"128151": {
|
| 1212 |
-
"content": "<|reserved_special_token_143|>",
|
| 1213 |
-
"lstrip": false,
|
| 1214 |
-
"normalized": false,
|
| 1215 |
-
"rstrip": false,
|
| 1216 |
-
"single_word": false,
|
| 1217 |
-
"special": true
|
| 1218 |
-
},
|
| 1219 |
-
"128152": {
|
| 1220 |
-
"content": "<|reserved_special_token_144|>",
|
| 1221 |
-
"lstrip": false,
|
| 1222 |
-
"normalized": false,
|
| 1223 |
-
"rstrip": false,
|
| 1224 |
-
"single_word": false,
|
| 1225 |
-
"special": true
|
| 1226 |
-
},
|
| 1227 |
-
"128153": {
|
| 1228 |
-
"content": "<|reserved_special_token_145|>",
|
| 1229 |
-
"lstrip": false,
|
| 1230 |
-
"normalized": false,
|
| 1231 |
-
"rstrip": false,
|
| 1232 |
-
"single_word": false,
|
| 1233 |
-
"special": true
|
| 1234 |
-
},
|
| 1235 |
-
"128154": {
|
| 1236 |
-
"content": "<|reserved_special_token_146|>",
|
| 1237 |
-
"lstrip": false,
|
| 1238 |
-
"normalized": false,
|
| 1239 |
-
"rstrip": false,
|
| 1240 |
-
"single_word": false,
|
| 1241 |
-
"special": true
|
| 1242 |
-
},
|
| 1243 |
-
"128155": {
|
| 1244 |
-
"content": "<|reserved_special_token_147|>",
|
| 1245 |
-
"lstrip": false,
|
| 1246 |
-
"normalized": false,
|
| 1247 |
-
"rstrip": false,
|
| 1248 |
-
"single_word": false,
|
| 1249 |
-
"special": true
|
| 1250 |
-
},
|
| 1251 |
-
"128156": {
|
| 1252 |
-
"content": "<|reserved_special_token_148|>",
|
| 1253 |
-
"lstrip": false,
|
| 1254 |
-
"normalized": false,
|
| 1255 |
-
"rstrip": false,
|
| 1256 |
-
"single_word": false,
|
| 1257 |
-
"special": true
|
| 1258 |
-
},
|
| 1259 |
-
"128157": {
|
| 1260 |
-
"content": "<|reserved_special_token_149|>",
|
| 1261 |
-
"lstrip": false,
|
| 1262 |
-
"normalized": false,
|
| 1263 |
-
"rstrip": false,
|
| 1264 |
-
"single_word": false,
|
| 1265 |
-
"special": true
|
| 1266 |
-
},
|
| 1267 |
-
"128158": {
|
| 1268 |
-
"content": "<|reserved_special_token_150|>",
|
| 1269 |
-
"lstrip": false,
|
| 1270 |
-
"normalized": false,
|
| 1271 |
-
"rstrip": false,
|
| 1272 |
-
"single_word": false,
|
| 1273 |
-
"special": true
|
| 1274 |
-
},
|
| 1275 |
-
"128159": {
|
| 1276 |
-
"content": "<|reserved_special_token_151|>",
|
| 1277 |
-
"lstrip": false,
|
| 1278 |
-
"normalized": false,
|
| 1279 |
-
"rstrip": false,
|
| 1280 |
-
"single_word": false,
|
| 1281 |
-
"special": true
|
| 1282 |
-
},
|
| 1283 |
-
"128160": {
|
| 1284 |
-
"content": "<|reserved_special_token_152|>",
|
| 1285 |
-
"lstrip": false,
|
| 1286 |
-
"normalized": false,
|
| 1287 |
-
"rstrip": false,
|
| 1288 |
-
"single_word": false,
|
| 1289 |
-
"special": true
|
| 1290 |
-
},
|
| 1291 |
-
"128161": {
|
| 1292 |
-
"content": "<|reserved_special_token_153|>",
|
| 1293 |
-
"lstrip": false,
|
| 1294 |
-
"normalized": false,
|
| 1295 |
-
"rstrip": false,
|
| 1296 |
-
"single_word": false,
|
| 1297 |
-
"special": true
|
| 1298 |
-
},
|
| 1299 |
-
"128162": {
|
| 1300 |
-
"content": "<|reserved_special_token_154|>",
|
| 1301 |
-
"lstrip": false,
|
| 1302 |
-
"normalized": false,
|
| 1303 |
-
"rstrip": false,
|
| 1304 |
-
"single_word": false,
|
| 1305 |
-
"special": true
|
| 1306 |
-
},
|
| 1307 |
-
"128163": {
|
| 1308 |
-
"content": "<|reserved_special_token_155|>",
|
| 1309 |
-
"lstrip": false,
|
| 1310 |
-
"normalized": false,
|
| 1311 |
-
"rstrip": false,
|
| 1312 |
-
"single_word": false,
|
| 1313 |
-
"special": true
|
| 1314 |
-
},
|
| 1315 |
-
"128164": {
|
| 1316 |
-
"content": "<|reserved_special_token_156|>",
|
| 1317 |
-
"lstrip": false,
|
| 1318 |
-
"normalized": false,
|
| 1319 |
-
"rstrip": false,
|
| 1320 |
-
"single_word": false,
|
| 1321 |
-
"special": true
|
| 1322 |
-
},
|
| 1323 |
-
"128165": {
|
| 1324 |
-
"content": "<|reserved_special_token_157|>",
|
| 1325 |
-
"lstrip": false,
|
| 1326 |
-
"normalized": false,
|
| 1327 |
-
"rstrip": false,
|
| 1328 |
-
"single_word": false,
|
| 1329 |
-
"special": true
|
| 1330 |
-
},
|
| 1331 |
-
"128166": {
|
| 1332 |
-
"content": "<|reserved_special_token_158|>",
|
| 1333 |
-
"lstrip": false,
|
| 1334 |
-
"normalized": false,
|
| 1335 |
-
"rstrip": false,
|
| 1336 |
-
"single_word": false,
|
| 1337 |
-
"special": true
|
| 1338 |
-
},
|
| 1339 |
-
"128167": {
|
| 1340 |
-
"content": "<|reserved_special_token_159|>",
|
| 1341 |
-
"lstrip": false,
|
| 1342 |
-
"normalized": false,
|
| 1343 |
-
"rstrip": false,
|
| 1344 |
-
"single_word": false,
|
| 1345 |
-
"special": true
|
| 1346 |
-
},
|
| 1347 |
-
"128168": {
|
| 1348 |
-
"content": "<|reserved_special_token_160|>",
|
| 1349 |
-
"lstrip": false,
|
| 1350 |
-
"normalized": false,
|
| 1351 |
-
"rstrip": false,
|
| 1352 |
-
"single_word": false,
|
| 1353 |
-
"special": true
|
| 1354 |
-
},
|
| 1355 |
-
"128169": {
|
| 1356 |
-
"content": "<|reserved_special_token_161|>",
|
| 1357 |
-
"lstrip": false,
|
| 1358 |
-
"normalized": false,
|
| 1359 |
-
"rstrip": false,
|
| 1360 |
-
"single_word": false,
|
| 1361 |
-
"special": true
|
| 1362 |
-
},
|
| 1363 |
-
"128170": {
|
| 1364 |
-
"content": "<|reserved_special_token_162|>",
|
| 1365 |
-
"lstrip": false,
|
| 1366 |
-
"normalized": false,
|
| 1367 |
-
"rstrip": false,
|
| 1368 |
-
"single_word": false,
|
| 1369 |
-
"special": true
|
| 1370 |
-
},
|
| 1371 |
-
"128171": {
|
| 1372 |
-
"content": "<|reserved_special_token_163|>",
|
| 1373 |
-
"lstrip": false,
|
| 1374 |
-
"normalized": false,
|
| 1375 |
-
"rstrip": false,
|
| 1376 |
-
"single_word": false,
|
| 1377 |
-
"special": true
|
| 1378 |
-
},
|
| 1379 |
-
"128172": {
|
| 1380 |
-
"content": "<|reserved_special_token_164|>",
|
| 1381 |
-
"lstrip": false,
|
| 1382 |
-
"normalized": false,
|
| 1383 |
-
"rstrip": false,
|
| 1384 |
-
"single_word": false,
|
| 1385 |
-
"special": true
|
| 1386 |
-
},
|
| 1387 |
-
"128173": {
|
| 1388 |
-
"content": "<|reserved_special_token_165|>",
|
| 1389 |
-
"lstrip": false,
|
| 1390 |
-
"normalized": false,
|
| 1391 |
-
"rstrip": false,
|
| 1392 |
-
"single_word": false,
|
| 1393 |
-
"special": true
|
| 1394 |
-
},
|
| 1395 |
-
"128174": {
|
| 1396 |
-
"content": "<|reserved_special_token_166|>",
|
| 1397 |
-
"lstrip": false,
|
| 1398 |
-
"normalized": false,
|
| 1399 |
-
"rstrip": false,
|
| 1400 |
-
"single_word": false,
|
| 1401 |
-
"special": true
|
| 1402 |
-
},
|
| 1403 |
-
"128175": {
|
| 1404 |
-
"content": "<|reserved_special_token_167|>",
|
| 1405 |
-
"lstrip": false,
|
| 1406 |
-
"normalized": false,
|
| 1407 |
-
"rstrip": false,
|
| 1408 |
-
"single_word": false,
|
| 1409 |
-
"special": true
|
| 1410 |
-
},
|
| 1411 |
-
"128176": {
|
| 1412 |
-
"content": "<|reserved_special_token_168|>",
|
| 1413 |
-
"lstrip": false,
|
| 1414 |
-
"normalized": false,
|
| 1415 |
-
"rstrip": false,
|
| 1416 |
-
"single_word": false,
|
| 1417 |
-
"special": true
|
| 1418 |
-
},
|
| 1419 |
-
"128177": {
|
| 1420 |
-
"content": "<|reserved_special_token_169|>",
|
| 1421 |
-
"lstrip": false,
|
| 1422 |
-
"normalized": false,
|
| 1423 |
-
"rstrip": false,
|
| 1424 |
-
"single_word": false,
|
| 1425 |
-
"special": true
|
| 1426 |
-
},
|
| 1427 |
-
"128178": {
|
| 1428 |
-
"content": "<|reserved_special_token_170|>",
|
| 1429 |
-
"lstrip": false,
|
| 1430 |
-
"normalized": false,
|
| 1431 |
-
"rstrip": false,
|
| 1432 |
-
"single_word": false,
|
| 1433 |
-
"special": true
|
| 1434 |
-
},
|
| 1435 |
-
"128179": {
|
| 1436 |
-
"content": "<|reserved_special_token_171|>",
|
| 1437 |
-
"lstrip": false,
|
| 1438 |
-
"normalized": false,
|
| 1439 |
-
"rstrip": false,
|
| 1440 |
-
"single_word": false,
|
| 1441 |
-
"special": true
|
| 1442 |
-
},
|
| 1443 |
-
"128180": {
|
| 1444 |
-
"content": "<|reserved_special_token_172|>",
|
| 1445 |
-
"lstrip": false,
|
| 1446 |
-
"normalized": false,
|
| 1447 |
-
"rstrip": false,
|
| 1448 |
-
"single_word": false,
|
| 1449 |
-
"special": true
|
| 1450 |
-
},
|
| 1451 |
-
"128181": {
|
| 1452 |
-
"content": "<|reserved_special_token_173|>",
|
| 1453 |
-
"lstrip": false,
|
| 1454 |
-
"normalized": false,
|
| 1455 |
-
"rstrip": false,
|
| 1456 |
-
"single_word": false,
|
| 1457 |
-
"special": true
|
| 1458 |
-
},
|
| 1459 |
-
"128182": {
|
| 1460 |
-
"content": "<|reserved_special_token_174|>",
|
| 1461 |
-
"lstrip": false,
|
| 1462 |
-
"normalized": false,
|
| 1463 |
-
"rstrip": false,
|
| 1464 |
-
"single_word": false,
|
| 1465 |
-
"special": true
|
| 1466 |
-
},
|
| 1467 |
-
"128183": {
|
| 1468 |
-
"content": "<|reserved_special_token_175|>",
|
| 1469 |
-
"lstrip": false,
|
| 1470 |
-
"normalized": false,
|
| 1471 |
-
"rstrip": false,
|
| 1472 |
-
"single_word": false,
|
| 1473 |
-
"special": true
|
| 1474 |
-
},
|
| 1475 |
-
"128184": {
|
| 1476 |
-
"content": "<|reserved_special_token_176|>",
|
| 1477 |
-
"lstrip": false,
|
| 1478 |
-
"normalized": false,
|
| 1479 |
-
"rstrip": false,
|
| 1480 |
-
"single_word": false,
|
| 1481 |
-
"special": true
|
| 1482 |
-
},
|
| 1483 |
-
"128185": {
|
| 1484 |
-
"content": "<|reserved_special_token_177|>",
|
| 1485 |
-
"lstrip": false,
|
| 1486 |
-
"normalized": false,
|
| 1487 |
-
"rstrip": false,
|
| 1488 |
-
"single_word": false,
|
| 1489 |
-
"special": true
|
| 1490 |
-
},
|
| 1491 |
-
"128186": {
|
| 1492 |
-
"content": "<|reserved_special_token_178|>",
|
| 1493 |
-
"lstrip": false,
|
| 1494 |
-
"normalized": false,
|
| 1495 |
-
"rstrip": false,
|
| 1496 |
-
"single_word": false,
|
| 1497 |
-
"special": true
|
| 1498 |
-
},
|
| 1499 |
-
"128187": {
|
| 1500 |
-
"content": "<|reserved_special_token_179|>",
|
| 1501 |
-
"lstrip": false,
|
| 1502 |
-
"normalized": false,
|
| 1503 |
-
"rstrip": false,
|
| 1504 |
-
"single_word": false,
|
| 1505 |
-
"special": true
|
| 1506 |
-
},
|
| 1507 |
-
"128188": {
|
| 1508 |
-
"content": "<|reserved_special_token_180|>",
|
| 1509 |
-
"lstrip": false,
|
| 1510 |
-
"normalized": false,
|
| 1511 |
-
"rstrip": false,
|
| 1512 |
-
"single_word": false,
|
| 1513 |
-
"special": true
|
| 1514 |
-
},
|
| 1515 |
-
"128189": {
|
| 1516 |
-
"content": "<|reserved_special_token_181|>",
|
| 1517 |
-
"lstrip": false,
|
| 1518 |
-
"normalized": false,
|
| 1519 |
-
"rstrip": false,
|
| 1520 |
-
"single_word": false,
|
| 1521 |
-
"special": true
|
| 1522 |
-
},
|
| 1523 |
-
"128190": {
|
| 1524 |
-
"content": "<|reserved_special_token_182|>",
|
| 1525 |
-
"lstrip": false,
|
| 1526 |
-
"normalized": false,
|
| 1527 |
-
"rstrip": false,
|
| 1528 |
-
"single_word": false,
|
| 1529 |
-
"special": true
|
| 1530 |
-
},
|
| 1531 |
-
"128191": {
|
| 1532 |
-
"content": "<|reserved_special_token_183|>",
|
| 1533 |
-
"lstrip": false,
|
| 1534 |
-
"normalized": false,
|
| 1535 |
-
"rstrip": false,
|
| 1536 |
-
"single_word": false,
|
| 1537 |
-
"special": true
|
| 1538 |
-
},
|
| 1539 |
-
"128192": {
|
| 1540 |
-
"content": "<|reserved_special_token_184|>",
|
| 1541 |
-
"lstrip": false,
|
| 1542 |
-
"normalized": false,
|
| 1543 |
-
"rstrip": false,
|
| 1544 |
-
"single_word": false,
|
| 1545 |
-
"special": true
|
| 1546 |
-
},
|
| 1547 |
-
"128193": {
|
| 1548 |
-
"content": "<|reserved_special_token_185|>",
|
| 1549 |
-
"lstrip": false,
|
| 1550 |
-
"normalized": false,
|
| 1551 |
-
"rstrip": false,
|
| 1552 |
-
"single_word": false,
|
| 1553 |
-
"special": true
|
| 1554 |
-
},
|
| 1555 |
-
"128194": {
|
| 1556 |
-
"content": "<|reserved_special_token_186|>",
|
| 1557 |
-
"lstrip": false,
|
| 1558 |
-
"normalized": false,
|
| 1559 |
-
"rstrip": false,
|
| 1560 |
-
"single_word": false,
|
| 1561 |
-
"special": true
|
| 1562 |
-
},
|
| 1563 |
-
"128195": {
|
| 1564 |
-
"content": "<|reserved_special_token_187|>",
|
| 1565 |
-
"lstrip": false,
|
| 1566 |
-
"normalized": false,
|
| 1567 |
-
"rstrip": false,
|
| 1568 |
-
"single_word": false,
|
| 1569 |
-
"special": true
|
| 1570 |
-
},
|
| 1571 |
-
"128196": {
|
| 1572 |
-
"content": "<|reserved_special_token_188|>",
|
| 1573 |
-
"lstrip": false,
|
| 1574 |
-
"normalized": false,
|
| 1575 |
-
"rstrip": false,
|
| 1576 |
-
"single_word": false,
|
| 1577 |
-
"special": true
|
| 1578 |
-
},
|
| 1579 |
-
"128197": {
|
| 1580 |
-
"content": "<|reserved_special_token_189|>",
|
| 1581 |
-
"lstrip": false,
|
| 1582 |
-
"normalized": false,
|
| 1583 |
-
"rstrip": false,
|
| 1584 |
-
"single_word": false,
|
| 1585 |
-
"special": true
|
| 1586 |
-
},
|
| 1587 |
-
"128198": {
|
| 1588 |
-
"content": "<|reserved_special_token_190|>",
|
| 1589 |
-
"lstrip": false,
|
| 1590 |
-
"normalized": false,
|
| 1591 |
-
"rstrip": false,
|
| 1592 |
-
"single_word": false,
|
| 1593 |
-
"special": true
|
| 1594 |
-
},
|
| 1595 |
-
"128199": {
|
| 1596 |
-
"content": "<|reserved_special_token_191|>",
|
| 1597 |
-
"lstrip": false,
|
| 1598 |
-
"normalized": false,
|
| 1599 |
-
"rstrip": false,
|
| 1600 |
-
"single_word": false,
|
| 1601 |
-
"special": true
|
| 1602 |
-
},
|
| 1603 |
-
"128200": {
|
| 1604 |
-
"content": "<|reserved_special_token_192|>",
|
| 1605 |
-
"lstrip": false,
|
| 1606 |
-
"normalized": false,
|
| 1607 |
-
"rstrip": false,
|
| 1608 |
-
"single_word": false,
|
| 1609 |
-
"special": true
|
| 1610 |
-
},
|
| 1611 |
-
"128201": {
|
| 1612 |
-
"content": "<|reserved_special_token_193|>",
|
| 1613 |
-
"lstrip": false,
|
| 1614 |
-
"normalized": false,
|
| 1615 |
-
"rstrip": false,
|
| 1616 |
-
"single_word": false,
|
| 1617 |
-
"special": true
|
| 1618 |
-
},
|
| 1619 |
-
"128202": {
|
| 1620 |
-
"content": "<|reserved_special_token_194|>",
|
| 1621 |
-
"lstrip": false,
|
| 1622 |
-
"normalized": false,
|
| 1623 |
-
"rstrip": false,
|
| 1624 |
-
"single_word": false,
|
| 1625 |
-
"special": true
|
| 1626 |
-
},
|
| 1627 |
-
"128203": {
|
| 1628 |
-
"content": "<|reserved_special_token_195|>",
|
| 1629 |
-
"lstrip": false,
|
| 1630 |
-
"normalized": false,
|
| 1631 |
-
"rstrip": false,
|
| 1632 |
-
"single_word": false,
|
| 1633 |
-
"special": true
|
| 1634 |
-
},
|
| 1635 |
-
"128204": {
|
| 1636 |
-
"content": "<|reserved_special_token_196|>",
|
| 1637 |
-
"lstrip": false,
|
| 1638 |
-
"normalized": false,
|
| 1639 |
-
"rstrip": false,
|
| 1640 |
-
"single_word": false,
|
| 1641 |
-
"special": true
|
| 1642 |
-
},
|
| 1643 |
-
"128205": {
|
| 1644 |
-
"content": "<|reserved_special_token_197|>",
|
| 1645 |
-
"lstrip": false,
|
| 1646 |
-
"normalized": false,
|
| 1647 |
-
"rstrip": false,
|
| 1648 |
-
"single_word": false,
|
| 1649 |
-
"special": true
|
| 1650 |
-
},
|
| 1651 |
-
"128206": {
|
| 1652 |
-
"content": "<|reserved_special_token_198|>",
|
| 1653 |
-
"lstrip": false,
|
| 1654 |
-
"normalized": false,
|
| 1655 |
-
"rstrip": false,
|
| 1656 |
-
"single_word": false,
|
| 1657 |
-
"special": true
|
| 1658 |
-
},
|
| 1659 |
-
"128207": {
|
| 1660 |
-
"content": "<|reserved_special_token_199|>",
|
| 1661 |
-
"lstrip": false,
|
| 1662 |
-
"normalized": false,
|
| 1663 |
-
"rstrip": false,
|
| 1664 |
-
"single_word": false,
|
| 1665 |
-
"special": true
|
| 1666 |
-
},
|
| 1667 |
-
"128208": {
|
| 1668 |
-
"content": "<|reserved_special_token_200|>",
|
| 1669 |
-
"lstrip": false,
|
| 1670 |
-
"normalized": false,
|
| 1671 |
-
"rstrip": false,
|
| 1672 |
-
"single_word": false,
|
| 1673 |
-
"special": true
|
| 1674 |
-
},
|
| 1675 |
-
"128209": {
|
| 1676 |
-
"content": "<|reserved_special_token_201|>",
|
| 1677 |
-
"lstrip": false,
|
| 1678 |
-
"normalized": false,
|
| 1679 |
-
"rstrip": false,
|
| 1680 |
-
"single_word": false,
|
| 1681 |
-
"special": true
|
| 1682 |
-
},
|
| 1683 |
-
"128210": {
|
| 1684 |
-
"content": "<|reserved_special_token_202|>",
|
| 1685 |
-
"lstrip": false,
|
| 1686 |
-
"normalized": false,
|
| 1687 |
-
"rstrip": false,
|
| 1688 |
-
"single_word": false,
|
| 1689 |
-
"special": true
|
| 1690 |
-
},
|
| 1691 |
-
"128211": {
|
| 1692 |
-
"content": "<|reserved_special_token_203|>",
|
| 1693 |
-
"lstrip": false,
|
| 1694 |
-
"normalized": false,
|
| 1695 |
-
"rstrip": false,
|
| 1696 |
-
"single_word": false,
|
| 1697 |
-
"special": true
|
| 1698 |
-
},
|
| 1699 |
-
"128212": {
|
| 1700 |
-
"content": "<|reserved_special_token_204|>",
|
| 1701 |
-
"lstrip": false,
|
| 1702 |
-
"normalized": false,
|
| 1703 |
-
"rstrip": false,
|
| 1704 |
-
"single_word": false,
|
| 1705 |
-
"special": true
|
| 1706 |
-
},
|
| 1707 |
-
"128213": {
|
| 1708 |
-
"content": "<|reserved_special_token_205|>",
|
| 1709 |
-
"lstrip": false,
|
| 1710 |
-
"normalized": false,
|
| 1711 |
-
"rstrip": false,
|
| 1712 |
-
"single_word": false,
|
| 1713 |
-
"special": true
|
| 1714 |
-
},
|
| 1715 |
-
"128214": {
|
| 1716 |
-
"content": "<|reserved_special_token_206|>",
|
| 1717 |
-
"lstrip": false,
|
| 1718 |
-
"normalized": false,
|
| 1719 |
-
"rstrip": false,
|
| 1720 |
-
"single_word": false,
|
| 1721 |
-
"special": true
|
| 1722 |
-
},
|
| 1723 |
-
"128215": {
|
| 1724 |
-
"content": "<|reserved_special_token_207|>",
|
| 1725 |
-
"lstrip": false,
|
| 1726 |
-
"normalized": false,
|
| 1727 |
-
"rstrip": false,
|
| 1728 |
-
"single_word": false,
|
| 1729 |
-
"special": true
|
| 1730 |
-
},
|
| 1731 |
-
"128216": {
|
| 1732 |
-
"content": "<|reserved_special_token_208|>",
|
| 1733 |
-
"lstrip": false,
|
| 1734 |
-
"normalized": false,
|
| 1735 |
-
"rstrip": false,
|
| 1736 |
-
"single_word": false,
|
| 1737 |
-
"special": true
|
| 1738 |
-
},
|
| 1739 |
-
"128217": {
|
| 1740 |
-
"content": "<|reserved_special_token_209|>",
|
| 1741 |
-
"lstrip": false,
|
| 1742 |
-
"normalized": false,
|
| 1743 |
-
"rstrip": false,
|
| 1744 |
-
"single_word": false,
|
| 1745 |
-
"special": true
|
| 1746 |
-
},
|
| 1747 |
-
"128218": {
|
| 1748 |
-
"content": "<|reserved_special_token_210|>",
|
| 1749 |
-
"lstrip": false,
|
| 1750 |
-
"normalized": false,
|
| 1751 |
-
"rstrip": false,
|
| 1752 |
-
"single_word": false,
|
| 1753 |
-
"special": true
|
| 1754 |
-
},
|
| 1755 |
-
"128219": {
|
| 1756 |
-
"content": "<|reserved_special_token_211|>",
|
| 1757 |
-
"lstrip": false,
|
| 1758 |
-
"normalized": false,
|
| 1759 |
-
"rstrip": false,
|
| 1760 |
-
"single_word": false,
|
| 1761 |
-
"special": true
|
| 1762 |
-
},
|
| 1763 |
-
"128220": {
|
| 1764 |
-
"content": "<|reserved_special_token_212|>",
|
| 1765 |
-
"lstrip": false,
|
| 1766 |
-
"normalized": false,
|
| 1767 |
-
"rstrip": false,
|
| 1768 |
-
"single_word": false,
|
| 1769 |
-
"special": true
|
| 1770 |
-
},
|
| 1771 |
-
"128221": {
|
| 1772 |
-
"content": "<|reserved_special_token_213|>",
|
| 1773 |
-
"lstrip": false,
|
| 1774 |
-
"normalized": false,
|
| 1775 |
-
"rstrip": false,
|
| 1776 |
-
"single_word": false,
|
| 1777 |
-
"special": true
|
| 1778 |
-
},
|
| 1779 |
-
"128222": {
|
| 1780 |
-
"content": "<|reserved_special_token_214|>",
|
| 1781 |
-
"lstrip": false,
|
| 1782 |
-
"normalized": false,
|
| 1783 |
-
"rstrip": false,
|
| 1784 |
-
"single_word": false,
|
| 1785 |
-
"special": true
|
| 1786 |
-
},
|
| 1787 |
-
"128223": {
|
| 1788 |
-
"content": "<|reserved_special_token_215|>",
|
| 1789 |
-
"lstrip": false,
|
| 1790 |
-
"normalized": false,
|
| 1791 |
-
"rstrip": false,
|
| 1792 |
-
"single_word": false,
|
| 1793 |
-
"special": true
|
| 1794 |
-
},
|
| 1795 |
-
"128224": {
|
| 1796 |
-
"content": "<|reserved_special_token_216|>",
|
| 1797 |
-
"lstrip": false,
|
| 1798 |
-
"normalized": false,
|
| 1799 |
-
"rstrip": false,
|
| 1800 |
-
"single_word": false,
|
| 1801 |
-
"special": true
|
| 1802 |
-
},
|
| 1803 |
-
"128225": {
|
| 1804 |
-
"content": "<|reserved_special_token_217|>",
|
| 1805 |
-
"lstrip": false,
|
| 1806 |
-
"normalized": false,
|
| 1807 |
-
"rstrip": false,
|
| 1808 |
-
"single_word": false,
|
| 1809 |
-
"special": true
|
| 1810 |
-
},
|
| 1811 |
-
"128226": {
|
| 1812 |
-
"content": "<|reserved_special_token_218|>",
|
| 1813 |
-
"lstrip": false,
|
| 1814 |
-
"normalized": false,
|
| 1815 |
-
"rstrip": false,
|
| 1816 |
-
"single_word": false,
|
| 1817 |
-
"special": true
|
| 1818 |
-
},
|
| 1819 |
-
"128227": {
|
| 1820 |
-
"content": "<|reserved_special_token_219|>",
|
| 1821 |
-
"lstrip": false,
|
| 1822 |
-
"normalized": false,
|
| 1823 |
-
"rstrip": false,
|
| 1824 |
-
"single_word": false,
|
| 1825 |
-
"special": true
|
| 1826 |
-
},
|
| 1827 |
-
"128228": {
|
| 1828 |
-
"content": "<|reserved_special_token_220|>",
|
| 1829 |
-
"lstrip": false,
|
| 1830 |
-
"normalized": false,
|
| 1831 |
-
"rstrip": false,
|
| 1832 |
-
"single_word": false,
|
| 1833 |
-
"special": true
|
| 1834 |
-
},
|
| 1835 |
-
"128229": {
|
| 1836 |
-
"content": "<|reserved_special_token_221|>",
|
| 1837 |
-
"lstrip": false,
|
| 1838 |
-
"normalized": false,
|
| 1839 |
-
"rstrip": false,
|
| 1840 |
-
"single_word": false,
|
| 1841 |
-
"special": true
|
| 1842 |
-
},
|
| 1843 |
-
"128230": {
|
| 1844 |
-
"content": "<|reserved_special_token_222|>",
|
| 1845 |
-
"lstrip": false,
|
| 1846 |
-
"normalized": false,
|
| 1847 |
-
"rstrip": false,
|
| 1848 |
-
"single_word": false,
|
| 1849 |
-
"special": true
|
| 1850 |
-
},
|
| 1851 |
-
"128231": {
|
| 1852 |
-
"content": "<|reserved_special_token_223|>",
|
| 1853 |
-
"lstrip": false,
|
| 1854 |
-
"normalized": false,
|
| 1855 |
-
"rstrip": false,
|
| 1856 |
-
"single_word": false,
|
| 1857 |
-
"special": true
|
| 1858 |
-
},
|
| 1859 |
-
"128232": {
|
| 1860 |
-
"content": "<|reserved_special_token_224|>",
|
| 1861 |
-
"lstrip": false,
|
| 1862 |
-
"normalized": false,
|
| 1863 |
-
"rstrip": false,
|
| 1864 |
-
"single_word": false,
|
| 1865 |
-
"special": true
|
| 1866 |
-
},
|
| 1867 |
-
"128233": {
|
| 1868 |
-
"content": "<|reserved_special_token_225|>",
|
| 1869 |
-
"lstrip": false,
|
| 1870 |
-
"normalized": false,
|
| 1871 |
-
"rstrip": false,
|
| 1872 |
-
"single_word": false,
|
| 1873 |
-
"special": true
|
| 1874 |
-
},
|
| 1875 |
-
"128234": {
|
| 1876 |
-
"content": "<|reserved_special_token_226|>",
|
| 1877 |
-
"lstrip": false,
|
| 1878 |
-
"normalized": false,
|
| 1879 |
-
"rstrip": false,
|
| 1880 |
-
"single_word": false,
|
| 1881 |
-
"special": true
|
| 1882 |
-
},
|
| 1883 |
-
"128235": {
|
| 1884 |
-
"content": "<|reserved_special_token_227|>",
|
| 1885 |
-
"lstrip": false,
|
| 1886 |
-
"normalized": false,
|
| 1887 |
-
"rstrip": false,
|
| 1888 |
-
"single_word": false,
|
| 1889 |
-
"special": true
|
| 1890 |
-
},
|
| 1891 |
-
"128236": {
|
| 1892 |
-
"content": "<|reserved_special_token_228|>",
|
| 1893 |
-
"lstrip": false,
|
| 1894 |
-
"normalized": false,
|
| 1895 |
-
"rstrip": false,
|
| 1896 |
-
"single_word": false,
|
| 1897 |
-
"special": true
|
| 1898 |
-
},
|
| 1899 |
-
"128237": {
|
| 1900 |
-
"content": "<|reserved_special_token_229|>",
|
| 1901 |
-
"lstrip": false,
|
| 1902 |
-
"normalized": false,
|
| 1903 |
-
"rstrip": false,
|
| 1904 |
-
"single_word": false,
|
| 1905 |
-
"special": true
|
| 1906 |
-
},
|
| 1907 |
-
"128238": {
|
| 1908 |
-
"content": "<|reserved_special_token_230|>",
|
| 1909 |
-
"lstrip": false,
|
| 1910 |
-
"normalized": false,
|
| 1911 |
-
"rstrip": false,
|
| 1912 |
-
"single_word": false,
|
| 1913 |
-
"special": true
|
| 1914 |
-
},
|
| 1915 |
-
"128239": {
|
| 1916 |
-
"content": "<|reserved_special_token_231|>",
|
| 1917 |
-
"lstrip": false,
|
| 1918 |
-
"normalized": false,
|
| 1919 |
-
"rstrip": false,
|
| 1920 |
-
"single_word": false,
|
| 1921 |
-
"special": true
|
| 1922 |
-
},
|
| 1923 |
-
"128240": {
|
| 1924 |
-
"content": "<|reserved_special_token_232|>",
|
| 1925 |
-
"lstrip": false,
|
| 1926 |
-
"normalized": false,
|
| 1927 |
-
"rstrip": false,
|
| 1928 |
-
"single_word": false,
|
| 1929 |
-
"special": true
|
| 1930 |
-
},
|
| 1931 |
-
"128241": {
|
| 1932 |
-
"content": "<|reserved_special_token_233|>",
|
| 1933 |
-
"lstrip": false,
|
| 1934 |
-
"normalized": false,
|
| 1935 |
-
"rstrip": false,
|
| 1936 |
-
"single_word": false,
|
| 1937 |
-
"special": true
|
| 1938 |
-
},
|
| 1939 |
-
"128242": {
|
| 1940 |
-
"content": "<|reserved_special_token_234|>",
|
| 1941 |
-
"lstrip": false,
|
| 1942 |
-
"normalized": false,
|
| 1943 |
-
"rstrip": false,
|
| 1944 |
-
"single_word": false,
|
| 1945 |
-
"special": true
|
| 1946 |
-
},
|
| 1947 |
-
"128243": {
|
| 1948 |
-
"content": "<|reserved_special_token_235|>",
|
| 1949 |
-
"lstrip": false,
|
| 1950 |
-
"normalized": false,
|
| 1951 |
-
"rstrip": false,
|
| 1952 |
-
"single_word": false,
|
| 1953 |
-
"special": true
|
| 1954 |
-
},
|
| 1955 |
-
"128244": {
|
| 1956 |
-
"content": "<|reserved_special_token_236|>",
|
| 1957 |
-
"lstrip": false,
|
| 1958 |
-
"normalized": false,
|
| 1959 |
-
"rstrip": false,
|
| 1960 |
-
"single_word": false,
|
| 1961 |
-
"special": true
|
| 1962 |
-
},
|
| 1963 |
-
"128245": {
|
| 1964 |
-
"content": "<|reserved_special_token_237|>",
|
| 1965 |
-
"lstrip": false,
|
| 1966 |
-
"normalized": false,
|
| 1967 |
-
"rstrip": false,
|
| 1968 |
-
"single_word": false,
|
| 1969 |
-
"special": true
|
| 1970 |
-
},
|
| 1971 |
-
"128246": {
|
| 1972 |
-
"content": "<|reserved_special_token_238|>",
|
| 1973 |
-
"lstrip": false,
|
| 1974 |
-
"normalized": false,
|
| 1975 |
-
"rstrip": false,
|
| 1976 |
-
"single_word": false,
|
| 1977 |
-
"special": true
|
| 1978 |
-
},
|
| 1979 |
-
"128247": {
|
| 1980 |
-
"content": "<|reserved_special_token_239|>",
|
| 1981 |
-
"lstrip": false,
|
| 1982 |
-
"normalized": false,
|
| 1983 |
-
"rstrip": false,
|
| 1984 |
-
"single_word": false,
|
| 1985 |
-
"special": true
|
| 1986 |
-
},
|
| 1987 |
-
"128248": {
|
| 1988 |
-
"content": "<|reserved_special_token_240|>",
|
| 1989 |
-
"lstrip": false,
|
| 1990 |
-
"normalized": false,
|
| 1991 |
-
"rstrip": false,
|
| 1992 |
-
"single_word": false,
|
| 1993 |
-
"special": true
|
| 1994 |
-
},
|
| 1995 |
-
"128249": {
|
| 1996 |
-
"content": "<|reserved_special_token_241|>",
|
| 1997 |
-
"lstrip": false,
|
| 1998 |
-
"normalized": false,
|
| 1999 |
-
"rstrip": false,
|
| 2000 |
-
"single_word": false,
|
| 2001 |
-
"special": true
|
| 2002 |
-
},
|
| 2003 |
-
"128250": {
|
| 2004 |
-
"content": "<|reserved_special_token_242|>",
|
| 2005 |
-
"lstrip": false,
|
| 2006 |
-
"normalized": false,
|
| 2007 |
-
"rstrip": false,
|
| 2008 |
-
"single_word": false,
|
| 2009 |
-
"special": true
|
| 2010 |
-
},
|
| 2011 |
-
"128251": {
|
| 2012 |
-
"content": "<|reserved_special_token_243|>",
|
| 2013 |
-
"lstrip": false,
|
| 2014 |
-
"normalized": false,
|
| 2015 |
-
"rstrip": false,
|
| 2016 |
-
"single_word": false,
|
| 2017 |
-
"special": true
|
| 2018 |
-
},
|
| 2019 |
-
"128252": {
|
| 2020 |
-
"content": "<|reserved_special_token_244|>",
|
| 2021 |
-
"lstrip": false,
|
| 2022 |
-
"normalized": false,
|
| 2023 |
-
"rstrip": false,
|
| 2024 |
-
"single_word": false,
|
| 2025 |
-
"special": true
|
| 2026 |
-
},
|
| 2027 |
-
"128253": {
|
| 2028 |
-
"content": "<|reserved_special_token_245|>",
|
| 2029 |
-
"lstrip": false,
|
| 2030 |
-
"normalized": false,
|
| 2031 |
-
"rstrip": false,
|
| 2032 |
-
"single_word": false,
|
| 2033 |
-
"special": true
|
| 2034 |
-
},
|
| 2035 |
-
"128254": {
|
| 2036 |
-
"content": "<|reserved_special_token_246|>",
|
| 2037 |
-
"lstrip": false,
|
| 2038 |
-
"normalized": false,
|
| 2039 |
-
"rstrip": false,
|
| 2040 |
-
"single_word": false,
|
| 2041 |
-
"special": true
|
| 2042 |
-
},
|
| 2043 |
-
"128255": {
|
| 2044 |
-
"content": "<|reserved_special_token_247|>",
|
| 2045 |
-
"lstrip": false,
|
| 2046 |
-
"normalized": false,
|
| 2047 |
-
"rstrip": false,
|
| 2048 |
-
"single_word": false,
|
| 2049 |
-
"special": true
|
| 2050 |
-
}
|
| 2051 |
-
},
|
| 2052 |
-
"bos_token": "<|begin_of_text|>",
|
| 2053 |
-
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
| 2054 |
-
"clean_up_tokenization_spaces": true,
|
| 2055 |
-
"eos_token": "<|eot_id|>",
|
| 2056 |
-
"extra_special_tokens": {},
|
| 2057 |
-
"model_input_names": [
|
| 2058 |
-
"input_ids",
|
| 2059 |
-
"attention_mask"
|
| 2060 |
-
],
|
| 2061 |
-
"model_max_length": 131072,
|
| 2062 |
-
"pad_token": "<|eot_id|>",
|
| 2063 |
-
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2064 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/trainer_state.json
DELETED
|
@@ -1,1365 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 2.759571209800919,
|
| 5 |
-
"eval_steps": 100,
|
| 6 |
-
"global_step": 900,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.015313935681470138,
|
| 13 |
-
"grad_norm": 3.8326407564846536,
|
| 14 |
-
"learning_rate": 6.134969325153375e-07,
|
| 15 |
-
"loss": 1.3339,
|
| 16 |
-
"step": 5
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"epoch": 0.030627871362940276,
|
| 20 |
-
"grad_norm": 3.5496788557416803,
|
| 21 |
-
"learning_rate": 1.226993865030675e-06,
|
| 22 |
-
"loss": 1.3517,
|
| 23 |
-
"step": 10
|
| 24 |
-
},
|
| 25 |
-
{
|
| 26 |
-
"epoch": 0.045941807044410414,
|
| 27 |
-
"grad_norm": 2.292172802820395,
|
| 28 |
-
"learning_rate": 1.8404907975460124e-06,
|
| 29 |
-
"loss": 1.3142,
|
| 30 |
-
"step": 15
|
| 31 |
-
},
|
| 32 |
-
{
|
| 33 |
-
"epoch": 0.06125574272588055,
|
| 34 |
-
"grad_norm": 1.7775340318261912,
|
| 35 |
-
"learning_rate": 2.45398773006135e-06,
|
| 36 |
-
"loss": 1.2477,
|
| 37 |
-
"step": 20
|
| 38 |
-
},
|
| 39 |
-
{
|
| 40 |
-
"epoch": 0.07656967840735068,
|
| 41 |
-
"grad_norm": 1.4368794370978828,
|
| 42 |
-
"learning_rate": 3.0674846625766875e-06,
|
| 43 |
-
"loss": 1.2037,
|
| 44 |
-
"step": 25
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.09188361408882083,
|
| 48 |
-
"grad_norm": 1.061354555879628,
|
| 49 |
-
"learning_rate": 3.680981595092025e-06,
|
| 50 |
-
"loss": 1.1505,
|
| 51 |
-
"step": 30
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.10719754977029096,
|
| 55 |
-
"grad_norm": 0.8377616484610274,
|
| 56 |
-
"learning_rate": 4.294478527607362e-06,
|
| 57 |
-
"loss": 1.1179,
|
| 58 |
-
"step": 35
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"epoch": 0.1225114854517611,
|
| 62 |
-
"grad_norm": 0.7884987790196414,
|
| 63 |
-
"learning_rate": 4.9079754601227e-06,
|
| 64 |
-
"loss": 1.0735,
|
| 65 |
-
"step": 40
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 0.13782542113323124,
|
| 69 |
-
"grad_norm": 0.7279957151761491,
|
| 70 |
-
"learning_rate": 5.521472392638038e-06,
|
| 71 |
-
"loss": 1.0556,
|
| 72 |
-
"step": 45
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 0.15313935681470137,
|
| 76 |
-
"grad_norm": 0.6692858930956382,
|
| 77 |
-
"learning_rate": 6.134969325153375e-06,
|
| 78 |
-
"loss": 1.0294,
|
| 79 |
-
"step": 50
|
| 80 |
-
},
|
| 81 |
-
{
|
| 82 |
-
"epoch": 0.16845329249617153,
|
| 83 |
-
"grad_norm": 0.6401840707040195,
|
| 84 |
-
"learning_rate": 6.748466257668712e-06,
|
| 85 |
-
"loss": 1.0175,
|
| 86 |
-
"step": 55
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 0.18376722817764166,
|
| 90 |
-
"grad_norm": 0.6584204446837412,
|
| 91 |
-
"learning_rate": 7.36196319018405e-06,
|
| 92 |
-
"loss": 1.0283,
|
| 93 |
-
"step": 60
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.1990811638591118,
|
| 97 |
-
"grad_norm": 0.6647811794468166,
|
| 98 |
-
"learning_rate": 7.975460122699386e-06,
|
| 99 |
-
"loss": 0.9799,
|
| 100 |
-
"step": 65
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.21439509954058192,
|
| 104 |
-
"grad_norm": 0.6774675226534475,
|
| 105 |
-
"learning_rate": 8.588957055214725e-06,
|
| 106 |
-
"loss": 0.969,
|
| 107 |
-
"step": 70
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 0.22970903522205208,
|
| 111 |
-
"grad_norm": 0.6918496726012217,
|
| 112 |
-
"learning_rate": 9.202453987730062e-06,
|
| 113 |
-
"loss": 0.9787,
|
| 114 |
-
"step": 75
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 0.2450229709035222,
|
| 118 |
-
"grad_norm": 0.6740082248654927,
|
| 119 |
-
"learning_rate": 9.8159509202454e-06,
|
| 120 |
-
"loss": 0.9596,
|
| 121 |
-
"step": 80
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 0.26033690658499237,
|
| 125 |
-
"grad_norm": 0.6791518891702232,
|
| 126 |
-
"learning_rate": 1.0429447852760737e-05,
|
| 127 |
-
"loss": 0.9813,
|
| 128 |
-
"step": 85
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 0.27565084226646247,
|
| 132 |
-
"grad_norm": 0.7029695620068616,
|
| 133 |
-
"learning_rate": 1.1042944785276076e-05,
|
| 134 |
-
"loss": 0.9703,
|
| 135 |
-
"step": 90
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 0.29096477794793263,
|
| 139 |
-
"grad_norm": 0.6355433423695775,
|
| 140 |
-
"learning_rate": 1.1656441717791411e-05,
|
| 141 |
-
"loss": 0.9375,
|
| 142 |
-
"step": 95
|
| 143 |
-
},
|
| 144 |
-
{
|
| 145 |
-
"epoch": 0.30627871362940273,
|
| 146 |
-
"grad_norm": 0.6551855479751819,
|
| 147 |
-
"learning_rate": 1.226993865030675e-05,
|
| 148 |
-
"loss": 0.952,
|
| 149 |
-
"step": 100
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 0.30627871362940273,
|
| 153 |
-
"eval_loss": 0.964697003364563,
|
| 154 |
-
"eval_runtime": 3.4019,
|
| 155 |
-
"eval_samples_per_second": 36.45,
|
| 156 |
-
"eval_steps_per_second": 2.352,
|
| 157 |
-
"step": 100
|
| 158 |
-
},
|
| 159 |
-
{
|
| 160 |
-
"epoch": 0.3215926493108729,
|
| 161 |
-
"grad_norm": 0.6655305965463972,
|
| 162 |
-
"learning_rate": 1.2883435582822085e-05,
|
| 163 |
-
"loss": 0.9237,
|
| 164 |
-
"step": 105
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 0.33690658499234305,
|
| 168 |
-
"grad_norm": 0.7257201177401903,
|
| 169 |
-
"learning_rate": 1.3496932515337424e-05,
|
| 170 |
-
"loss": 0.9511,
|
| 171 |
-
"step": 110
|
| 172 |
-
},
|
| 173 |
-
{
|
| 174 |
-
"epoch": 0.35222052067381315,
|
| 175 |
-
"grad_norm": 0.7424667090609683,
|
| 176 |
-
"learning_rate": 1.4110429447852763e-05,
|
| 177 |
-
"loss": 0.9323,
|
| 178 |
-
"step": 115
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 0.3675344563552833,
|
| 182 |
-
"grad_norm": 0.7336582339806711,
|
| 183 |
-
"learning_rate": 1.47239263803681e-05,
|
| 184 |
-
"loss": 0.9449,
|
| 185 |
-
"step": 120
|
| 186 |
-
},
|
| 187 |
-
{
|
| 188 |
-
"epoch": 0.38284839203675347,
|
| 189 |
-
"grad_norm": 0.6851538651091853,
|
| 190 |
-
"learning_rate": 1.5337423312883436e-05,
|
| 191 |
-
"loss": 0.9133,
|
| 192 |
-
"step": 125
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"epoch": 0.3981623277182236,
|
| 196 |
-
"grad_norm": 0.7424313941044212,
|
| 197 |
-
"learning_rate": 1.5950920245398772e-05,
|
| 198 |
-
"loss": 0.9173,
|
| 199 |
-
"step": 130
|
| 200 |
-
},
|
| 201 |
-
{
|
| 202 |
-
"epoch": 0.41347626339969373,
|
| 203 |
-
"grad_norm": 0.7937170928985942,
|
| 204 |
-
"learning_rate": 1.656441717791411e-05,
|
| 205 |
-
"loss": 0.9348,
|
| 206 |
-
"step": 135
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 0.42879019908116384,
|
| 210 |
-
"grad_norm": 0.7668730085289572,
|
| 211 |
-
"learning_rate": 1.717791411042945e-05,
|
| 212 |
-
"loss": 0.9091,
|
| 213 |
-
"step": 140
|
| 214 |
-
},
|
| 215 |
-
{
|
| 216 |
-
"epoch": 0.444104134762634,
|
| 217 |
-
"grad_norm": 0.713212902268727,
|
| 218 |
-
"learning_rate": 1.7791411042944788e-05,
|
| 219 |
-
"loss": 0.9054,
|
| 220 |
-
"step": 145
|
| 221 |
-
},
|
| 222 |
-
{
|
| 223 |
-
"epoch": 0.45941807044410415,
|
| 224 |
-
"grad_norm": 0.8266274957992115,
|
| 225 |
-
"learning_rate": 1.8404907975460123e-05,
|
| 226 |
-
"loss": 0.9165,
|
| 227 |
-
"step": 150
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 0.47473200612557426,
|
| 231 |
-
"grad_norm": 0.7773849012810377,
|
| 232 |
-
"learning_rate": 1.9018404907975462e-05,
|
| 233 |
-
"loss": 0.9261,
|
| 234 |
-
"step": 155
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"epoch": 0.4900459418070444,
|
| 238 |
-
"grad_norm": 0.7698543962501324,
|
| 239 |
-
"learning_rate": 1.96319018404908e-05,
|
| 240 |
-
"loss": 0.8848,
|
| 241 |
-
"step": 160
|
| 242 |
-
},
|
| 243 |
-
{
|
| 244 |
-
"epoch": 0.5053598774885145,
|
| 245 |
-
"grad_norm": 0.7326492641075325,
|
| 246 |
-
"learning_rate": 1.9999908278985548e-05,
|
| 247 |
-
"loss": 0.9002,
|
| 248 |
-
"step": 165
|
| 249 |
-
},
|
| 250 |
-
{
|
| 251 |
-
"epoch": 0.5206738131699847,
|
| 252 |
-
"grad_norm": 0.725915155149828,
|
| 253 |
-
"learning_rate": 1.9998876436895888e-05,
|
| 254 |
-
"loss": 0.9064,
|
| 255 |
-
"step": 170
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 0.5359877488514548,
|
| 259 |
-
"grad_norm": 0.7137681931522117,
|
| 260 |
-
"learning_rate": 1.99966982201439e-05,
|
| 261 |
-
"loss": 0.9083,
|
| 262 |
-
"step": 175
|
| 263 |
-
},
|
| 264 |
-
{
|
| 265 |
-
"epoch": 0.5513016845329249,
|
| 266 |
-
"grad_norm": 0.8244990854189328,
|
| 267 |
-
"learning_rate": 1.9993373878462894e-05,
|
| 268 |
-
"loss": 0.8988,
|
| 269 |
-
"step": 180
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 0.5666156202143952,
|
| 273 |
-
"grad_norm": 0.7883005110592801,
|
| 274 |
-
"learning_rate": 1.99889037929898e-05,
|
| 275 |
-
"loss": 0.9021,
|
| 276 |
-
"step": 185
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"epoch": 0.5819295558958653,
|
| 280 |
-
"grad_norm": 0.7224060026030372,
|
| 281 |
-
"learning_rate": 1.9983288476221482e-05,
|
| 282 |
-
"loss": 0.8881,
|
| 283 |
-
"step": 190
|
| 284 |
-
},
|
| 285 |
-
{
|
| 286 |
-
"epoch": 0.5972434915773354,
|
| 287 |
-
"grad_norm": 0.7010662098507998,
|
| 288 |
-
"learning_rate": 1.9976528571955946e-05,
|
| 289 |
-
"loss": 0.8889,
|
| 290 |
-
"step": 195
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 0.6125574272588055,
|
| 294 |
-
"grad_norm": 0.7154815490781321,
|
| 295 |
-
"learning_rate": 1.9968624855218578e-05,
|
| 296 |
-
"loss": 0.8884,
|
| 297 |
-
"step": 200
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 0.6125574272588055,
|
| 301 |
-
"eval_loss": 0.9119902849197388,
|
| 302 |
-
"eval_runtime": 3.4604,
|
| 303 |
-
"eval_samples_per_second": 35.834,
|
| 304 |
-
"eval_steps_per_second": 2.312,
|
| 305 |
-
"step": 200
|
| 306 |
-
},
|
| 307 |
-
{
|
| 308 |
-
"epoch": 0.6278713629402757,
|
| 309 |
-
"grad_norm": 0.6984184509316927,
|
| 310 |
-
"learning_rate": 1.995957823217325e-05,
|
| 311 |
-
"loss": 0.9033,
|
| 312 |
-
"step": 205
|
| 313 |
-
},
|
| 314 |
-
{
|
| 315 |
-
"epoch": 0.6431852986217458,
|
| 316 |
-
"grad_norm": 0.7120998555383481,
|
| 317 |
-
"learning_rate": 1.9949389740018438e-05,
|
| 318 |
-
"loss": 0.8988,
|
| 319 |
-
"step": 210
|
| 320 |
-
},
|
| 321 |
-
{
|
| 322 |
-
"epoch": 0.6584992343032159,
|
| 323 |
-
"grad_norm": 0.66696186884436,
|
| 324 |
-
"learning_rate": 1.993806054686832e-05,
|
| 325 |
-
"loss": 0.8735,
|
| 326 |
-
"step": 215
|
| 327 |
-
},
|
| 328 |
-
{
|
| 329 |
-
"epoch": 0.6738131699846861,
|
| 330 |
-
"grad_norm": 0.7395425655626215,
|
| 331 |
-
"learning_rate": 1.9925591951618822e-05,
|
| 332 |
-
"loss": 0.9127,
|
| 333 |
-
"step": 220
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"epoch": 0.6891271056661562,
|
| 337 |
-
"grad_norm": 0.6960401538019414,
|
| 338 |
-
"learning_rate": 1.9911985383798737e-05,
|
| 339 |
-
"loss": 0.875,
|
| 340 |
-
"step": 225
|
| 341 |
-
},
|
| 342 |
-
{
|
| 343 |
-
"epoch": 0.7044410413476263,
|
| 344 |
-
"grad_norm": 0.7195874036136765,
|
| 345 |
-
"learning_rate": 1.9897242403405792e-05,
|
| 346 |
-
"loss": 0.8782,
|
| 347 |
-
"step": 230
|
| 348 |
-
},
|
| 349 |
-
{
|
| 350 |
-
"epoch": 0.7197549770290965,
|
| 351 |
-
"grad_norm": 0.7129931764921758,
|
| 352 |
-
"learning_rate": 1.9881364700727827e-05,
|
| 353 |
-
"loss": 0.8943,
|
| 354 |
-
"step": 235
|
| 355 |
-
},
|
| 356 |
-
{
|
| 357 |
-
"epoch": 0.7350689127105666,
|
| 358 |
-
"grad_norm": 0.690645634714852,
|
| 359 |
-
"learning_rate": 1.9864354096148966e-05,
|
| 360 |
-
"loss": 0.8782,
|
| 361 |
-
"step": 240
|
| 362 |
-
},
|
| 363 |
-
{
|
| 364 |
-
"epoch": 0.7503828483920367,
|
| 365 |
-
"grad_norm": 0.7055958514936376,
|
| 366 |
-
"learning_rate": 1.9846212539940955e-05,
|
| 367 |
-
"loss": 0.8867,
|
| 368 |
-
"step": 245
|
| 369 |
-
},
|
| 370 |
-
{
|
| 371 |
-
"epoch": 0.7656967840735069,
|
| 372 |
-
"grad_norm": 0.7517885221069497,
|
| 373 |
-
"learning_rate": 1.982694211203952e-05,
|
| 374 |
-
"loss": 0.8843,
|
| 375 |
-
"step": 250
|
| 376 |
-
},
|
| 377 |
-
{
|
| 378 |
-
"epoch": 0.781010719754977,
|
| 379 |
-
"grad_norm": 0.7270711746255435,
|
| 380 |
-
"learning_rate": 1.9806545021805922e-05,
|
| 381 |
-
"loss": 0.8757,
|
| 382 |
-
"step": 255
|
| 383 |
-
},
|
| 384 |
-
{
|
| 385 |
-
"epoch": 0.7963246554364471,
|
| 386 |
-
"grad_norm": 0.707252502344583,
|
| 387 |
-
"learning_rate": 1.9785023607773655e-05,
|
| 388 |
-
"loss": 0.8842,
|
| 389 |
-
"step": 260
|
| 390 |
-
},
|
| 391 |
-
{
|
| 392 |
-
"epoch": 0.8116385911179173,
|
| 393 |
-
"grad_norm": 0.8083132789219781,
|
| 394 |
-
"learning_rate": 1.976238033738033e-05,
|
| 395 |
-
"loss": 0.8578,
|
| 396 |
-
"step": 265
|
| 397 |
-
},
|
| 398 |
-
{
|
| 399 |
-
"epoch": 0.8269525267993875,
|
| 400 |
-
"grad_norm": 0.7287731737231247,
|
| 401 |
-
"learning_rate": 1.9738617806684767e-05,
|
| 402 |
-
"loss": 0.911,
|
| 403 |
-
"step": 270
|
| 404 |
-
},
|
| 405 |
-
{
|
| 406 |
-
"epoch": 0.8422664624808576,
|
| 407 |
-
"grad_norm": 0.7683997901360534,
|
| 408 |
-
"learning_rate": 1.9713738740069384e-05,
|
| 409 |
-
"loss": 0.8607,
|
| 410 |
-
"step": 275
|
| 411 |
-
},
|
| 412 |
-
{
|
| 413 |
-
"epoch": 0.8575803981623277,
|
| 414 |
-
"grad_norm": 0.6883196631913017,
|
| 415 |
-
"learning_rate": 1.9687745989927823e-05,
|
| 416 |
-
"loss": 0.8781,
|
| 417 |
-
"step": 280
|
| 418 |
-
},
|
| 419 |
-
{
|
| 420 |
-
"epoch": 0.8728943338437979,
|
| 421 |
-
"grad_norm": 0.7137416791751114,
|
| 422 |
-
"learning_rate": 1.966064253633793e-05,
|
| 423 |
-
"loss": 0.8675,
|
| 424 |
-
"step": 285
|
| 425 |
-
},
|
| 426 |
-
{
|
| 427 |
-
"epoch": 0.888208269525268,
|
| 428 |
-
"grad_norm": 0.800711538711323,
|
| 429 |
-
"learning_rate": 1.963243148672009e-05,
|
| 430 |
-
"loss": 0.8696,
|
| 431 |
-
"step": 290
|
| 432 |
-
},
|
| 433 |
-
{
|
| 434 |
-
"epoch": 0.9035222052067381,
|
| 435 |
-
"grad_norm": 0.7017619169785259,
|
| 436 |
-
"learning_rate": 1.960311607548096e-05,
|
| 437 |
-
"loss": 0.8724,
|
| 438 |
-
"step": 295
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"epoch": 0.9188361408882083,
|
| 442 |
-
"grad_norm": 0.7347091076360852,
|
| 443 |
-
"learning_rate": 1.957269966364263e-05,
|
| 444 |
-
"loss": 0.8753,
|
| 445 |
-
"step": 300
|
| 446 |
-
},
|
| 447 |
-
{
|
| 448 |
-
"epoch": 0.9188361408882083,
|
| 449 |
-
"eval_loss": 0.8846515417098999,
|
| 450 |
-
"eval_runtime": 3.4431,
|
| 451 |
-
"eval_samples_per_second": 36.014,
|
| 452 |
-
"eval_steps_per_second": 2.323,
|
| 453 |
-
"step": 300
|
| 454 |
-
},
|
| 455 |
-
{
|
| 456 |
-
"epoch": 0.9341500765696784,
|
| 457 |
-
"grad_norm": 0.6840257399223311,
|
| 458 |
-
"learning_rate": 1.9541185738457304e-05,
|
| 459 |
-
"loss": 0.8661,
|
| 460 |
-
"step": 305
|
| 461 |
-
},
|
| 462 |
-
{
|
| 463 |
-
"epoch": 0.9494640122511485,
|
| 464 |
-
"grad_norm": 0.6350789314835292,
|
| 465 |
-
"learning_rate": 1.9508577913007475e-05,
|
| 466 |
-
"loss": 0.866,
|
| 467 |
-
"step": 310
|
| 468 |
-
},
|
| 469 |
-
{
|
| 470 |
-
"epoch": 0.9647779479326187,
|
| 471 |
-
"grad_norm": 0.742666392443459,
|
| 472 |
-
"learning_rate": 1.9474879925791665e-05,
|
| 473 |
-
"loss": 0.8712,
|
| 474 |
-
"step": 315
|
| 475 |
-
},
|
| 476 |
-
{
|
| 477 |
-
"epoch": 0.9800918836140888,
|
| 478 |
-
"grad_norm": 0.7707700113231902,
|
| 479 |
-
"learning_rate": 1.944009564029584e-05,
|
| 480 |
-
"loss": 0.8656,
|
| 481 |
-
"step": 320
|
| 482 |
-
},
|
| 483 |
-
{
|
| 484 |
-
"epoch": 0.9954058192955589,
|
| 485 |
-
"grad_norm": 0.7026681496550549,
|
| 486 |
-
"learning_rate": 1.9404229044550432e-05,
|
| 487 |
-
"loss": 0.8707,
|
| 488 |
-
"step": 325
|
| 489 |
-
},
|
| 490 |
-
{
|
| 491 |
-
"epoch": 1.0122511485451762,
|
| 492 |
-
"grad_norm": 0.8698658929763603,
|
| 493 |
-
"learning_rate": 1.9367284250673126e-05,
|
| 494 |
-
"loss": 1.0103,
|
| 495 |
-
"step": 330
|
| 496 |
-
},
|
| 497 |
-
{
|
| 498 |
-
"epoch": 1.0275650842266462,
|
| 499 |
-
"grad_norm": 0.7696705674515646,
|
| 500 |
-
"learning_rate": 1.9329265494397386e-05,
|
| 501 |
-
"loss": 0.8254,
|
| 502 |
-
"step": 335
|
| 503 |
-
},
|
| 504 |
-
{
|
| 505 |
-
"epoch": 1.0428790199081164,
|
| 506 |
-
"grad_norm": 0.703085270940529,
|
| 507 |
-
"learning_rate": 1.929017713458685e-05,
|
| 508 |
-
"loss": 0.7994,
|
| 509 |
-
"step": 340
|
| 510 |
-
},
|
| 511 |
-
{
|
| 512 |
-
"epoch": 1.0581929555895866,
|
| 513 |
-
"grad_norm": 0.7281489106195598,
|
| 514 |
-
"learning_rate": 1.9250023652735573e-05,
|
| 515 |
-
"loss": 0.7997,
|
| 516 |
-
"step": 345
|
| 517 |
-
},
|
| 518 |
-
{
|
| 519 |
-
"epoch": 1.0735068912710566,
|
| 520 |
-
"grad_norm": 0.6721859356177987,
|
| 521 |
-
"learning_rate": 1.920880965245422e-05,
|
| 522 |
-
"loss": 0.8028,
|
| 523 |
-
"step": 350
|
| 524 |
-
},
|
| 525 |
-
{
|
| 526 |
-
"epoch": 1.0888208269525268,
|
| 527 |
-
"grad_norm": 0.6999456629939552,
|
| 528 |
-
"learning_rate": 1.9166539858942258e-05,
|
| 529 |
-
"loss": 0.7923,
|
| 530 |
-
"step": 355
|
| 531 |
-
},
|
| 532 |
-
{
|
| 533 |
-
"epoch": 1.104134762633997,
|
| 534 |
-
"grad_norm": 0.761057382772568,
|
| 535 |
-
"learning_rate": 1.912321911844622e-05,
|
| 536 |
-
"loss": 0.8023,
|
| 537 |
-
"step": 360
|
| 538 |
-
},
|
| 539 |
-
{
|
| 540 |
-
"epoch": 1.119448698315467,
|
| 541 |
-
"grad_norm": 0.7613985157569584,
|
| 542 |
-
"learning_rate": 1.907885239770408e-05,
|
| 543 |
-
"loss": 0.8171,
|
| 544 |
-
"step": 365
|
| 545 |
-
},
|
| 546 |
-
{
|
| 547 |
-
"epoch": 1.1347626339969372,
|
| 548 |
-
"grad_norm": 0.7130602486133167,
|
| 549 |
-
"learning_rate": 1.9033444783375806e-05,
|
| 550 |
-
"loss": 0.8136,
|
| 551 |
-
"step": 370
|
| 552 |
-
},
|
| 553 |
-
{
|
| 554 |
-
"epoch": 1.1500765696784074,
|
| 555 |
-
"grad_norm": 0.7290477717213912,
|
| 556 |
-
"learning_rate": 1.8987001481460177e-05,
|
| 557 |
-
"loss": 0.7956,
|
| 558 |
-
"step": 375
|
| 559 |
-
},
|
| 560 |
-
{
|
| 561 |
-
"epoch": 1.1653905053598774,
|
| 562 |
-
"grad_norm": 0.6942113670274667,
|
| 563 |
-
"learning_rate": 1.8939527816697917e-05,
|
| 564 |
-
"loss": 0.795,
|
| 565 |
-
"step": 380
|
| 566 |
-
},
|
| 567 |
-
{
|
| 568 |
-
"epoch": 1.1807044410413476,
|
| 569 |
-
"grad_norm": 0.7278550945084655,
|
| 570 |
-
"learning_rate": 1.8891029231961208e-05,
|
| 571 |
-
"loss": 0.8038,
|
| 572 |
-
"step": 385
|
| 573 |
-
},
|
| 574 |
-
{
|
| 575 |
-
"epoch": 1.1960183767228179,
|
| 576 |
-
"grad_norm": 0.7637922924754829,
|
| 577 |
-
"learning_rate": 1.8841511287629667e-05,
|
| 578 |
-
"loss": 0.7941,
|
| 579 |
-
"step": 390
|
| 580 |
-
},
|
| 581 |
-
{
|
| 582 |
-
"epoch": 1.2113323124042878,
|
| 583 |
-
"grad_norm": 0.7227667767094055,
|
| 584 |
-
"learning_rate": 1.8790979660952832e-05,
|
| 585 |
-
"loss": 0.7899,
|
| 586 |
-
"step": 395
|
| 587 |
-
},
|
| 588 |
-
{
|
| 589 |
-
"epoch": 1.226646248085758,
|
| 590 |
-
"grad_norm": 0.6856723635729023,
|
| 591 |
-
"learning_rate": 1.8739440145399295e-05,
|
| 592 |
-
"loss": 0.8037,
|
| 593 |
-
"step": 400
|
| 594 |
-
},
|
| 595 |
-
{
|
| 596 |
-
"epoch": 1.226646248085758,
|
| 597 |
-
"eval_loss": 0.8724085092544556,
|
| 598 |
-
"eval_runtime": 3.6883,
|
| 599 |
-
"eval_samples_per_second": 33.619,
|
| 600 |
-
"eval_steps_per_second": 2.169,
|
| 601 |
-
"step": 400
|
| 602 |
-
},
|
| 603 |
-
{
|
| 604 |
-
"epoch": 1.2419601837672283,
|
| 605 |
-
"grad_norm": 0.6585093868236329,
|
| 606 |
-
"learning_rate": 1.8686898649992437e-05,
|
| 607 |
-
"loss": 0.7969,
|
| 608 |
-
"step": 405
|
| 609 |
-
},
|
| 610 |
-
{
|
| 611 |
-
"epoch": 1.2572741194486983,
|
| 612 |
-
"grad_norm": 0.6787675213944868,
|
| 613 |
-
"learning_rate": 1.8633361198632987e-05,
|
| 614 |
-
"loss": 0.8077,
|
| 615 |
-
"step": 410
|
| 616 |
-
},
|
| 617 |
-
{
|
| 618 |
-
"epoch": 1.2725880551301685,
|
| 619 |
-
"grad_norm": 0.6808724401749536,
|
| 620 |
-
"learning_rate": 1.857883392940837e-05,
|
| 621 |
-
"loss": 0.8077,
|
| 622 |
-
"step": 415
|
| 623 |
-
},
|
| 624 |
-
{
|
| 625 |
-
"epoch": 1.2879019908116387,
|
| 626 |
-
"grad_norm": 0.6824672080638723,
|
| 627 |
-
"learning_rate": 1.8523323093888983e-05,
|
| 628 |
-
"loss": 0.8025,
|
| 629 |
-
"step": 420
|
| 630 |
-
},
|
| 631 |
-
{
|
| 632 |
-
"epoch": 1.3032159264931087,
|
| 633 |
-
"grad_norm": 0.6611632916751219,
|
| 634 |
-
"learning_rate": 1.8466835056411422e-05,
|
| 635 |
-
"loss": 0.7875,
|
| 636 |
-
"step": 425
|
| 637 |
-
},
|
| 638 |
-
{
|
| 639 |
-
"epoch": 1.318529862174579,
|
| 640 |
-
"grad_norm": 0.701746007873801,
|
| 641 |
-
"learning_rate": 1.8409376293348836e-05,
|
| 642 |
-
"loss": 0.794,
|
| 643 |
-
"step": 430
|
| 644 |
-
},
|
| 645 |
-
{
|
| 646 |
-
"epoch": 1.3338437978560491,
|
| 647 |
-
"grad_norm": 0.6668057827943388,
|
| 648 |
-
"learning_rate": 1.8350953392368408e-05,
|
| 649 |
-
"loss": 0.797,
|
| 650 |
-
"step": 435
|
| 651 |
-
},
|
| 652 |
-
{
|
| 653 |
-
"epoch": 1.349157733537519,
|
| 654 |
-
"grad_norm": 0.7077024335619939,
|
| 655 |
-
"learning_rate": 1.8291573051676063e-05,
|
| 656 |
-
"loss": 0.8257,
|
| 657 |
-
"step": 440
|
| 658 |
-
},
|
| 659 |
-
{
|
| 660 |
-
"epoch": 1.3644716692189893,
|
| 661 |
-
"grad_norm": 0.7168213984013295,
|
| 662 |
-
"learning_rate": 1.8231242079248512e-05,
|
| 663 |
-
"loss": 0.7934,
|
| 664 |
-
"step": 445
|
| 665 |
-
},
|
| 666 |
-
{
|
| 667 |
-
"epoch": 1.3797856049004595,
|
| 668 |
-
"grad_norm": 0.7308258264034365,
|
| 669 |
-
"learning_rate": 1.816996739205274e-05,
|
| 670 |
-
"loss": 0.8078,
|
| 671 |
-
"step": 450
|
| 672 |
-
},
|
| 673 |
-
{
|
| 674 |
-
"epoch": 1.3950995405819295,
|
| 675 |
-
"grad_norm": 0.7935757091141241,
|
| 676 |
-
"learning_rate": 1.810775601525296e-05,
|
| 677 |
-
"loss": 0.8172,
|
| 678 |
-
"step": 455
|
| 679 |
-
},
|
| 680 |
-
{
|
| 681 |
-
"epoch": 1.4104134762633997,
|
| 682 |
-
"grad_norm": 0.7960723044086886,
|
| 683 |
-
"learning_rate": 1.8044615081405153e-05,
|
| 684 |
-
"loss": 0.7973,
|
| 685 |
-
"step": 460
|
| 686 |
-
},
|
| 687 |
-
{
|
| 688 |
-
"epoch": 1.42572741194487,
|
| 689 |
-
"grad_norm": 0.7013219126306894,
|
| 690 |
-
"learning_rate": 1.7980551829639357e-05,
|
| 691 |
-
"loss": 0.7928,
|
| 692 |
-
"step": 465
|
| 693 |
-
},
|
| 694 |
-
{
|
| 695 |
-
"epoch": 1.44104134762634,
|
| 696 |
-
"grad_norm": 0.7030096980783208,
|
| 697 |
-
"learning_rate": 1.7915573604829684e-05,
|
| 698 |
-
"loss": 0.7891,
|
| 699 |
-
"step": 470
|
| 700 |
-
},
|
| 701 |
-
{
|
| 702 |
-
"epoch": 1.4563552833078102,
|
| 703 |
-
"grad_norm": 0.7129952798275541,
|
| 704 |
-
"learning_rate": 1.784968785675221e-05,
|
| 705 |
-
"loss": 0.7964,
|
| 706 |
-
"step": 475
|
| 707 |
-
},
|
| 708 |
-
{
|
| 709 |
-
"epoch": 1.4716692189892804,
|
| 710 |
-
"grad_norm": 0.7042351661303197,
|
| 711 |
-
"learning_rate": 1.7782902139230876e-05,
|
| 712 |
-
"loss": 0.7821,
|
| 713 |
-
"step": 480
|
| 714 |
-
},
|
| 715 |
-
{
|
| 716 |
-
"epoch": 1.4869831546707504,
|
| 717 |
-
"grad_norm": 0.7412846210916867,
|
| 718 |
-
"learning_rate": 1.7715224109271426e-05,
|
| 719 |
-
"loss": 0.7983,
|
| 720 |
-
"step": 485
|
| 721 |
-
},
|
| 722 |
-
{
|
| 723 |
-
"epoch": 1.5022970903522204,
|
| 724 |
-
"grad_norm": 0.7586380261564012,
|
| 725 |
-
"learning_rate": 1.764666152618355e-05,
|
| 726 |
-
"loss": 0.8167,
|
| 727 |
-
"step": 490
|
| 728 |
-
},
|
| 729 |
-
{
|
| 730 |
-
"epoch": 1.5176110260336908,
|
| 731 |
-
"grad_norm": 0.784243612804958,
|
| 732 |
-
"learning_rate": 1.7577222250691254e-05,
|
| 733 |
-
"loss": 0.8086,
|
| 734 |
-
"step": 495
|
| 735 |
-
},
|
| 736 |
-
{
|
| 737 |
-
"epoch": 1.5329249617151608,
|
| 738 |
-
"grad_norm": 0.6901397300587065,
|
| 739 |
-
"learning_rate": 1.7506914244031627e-05,
|
| 740 |
-
"loss": 0.7966,
|
| 741 |
-
"step": 500
|
| 742 |
-
},
|
| 743 |
-
{
|
| 744 |
-
"epoch": 1.5329249617151608,
|
| 745 |
-
"eval_loss": 0.8608717918395996,
|
| 746 |
-
"eval_runtime": 4.0604,
|
| 747 |
-
"eval_samples_per_second": 30.539,
|
| 748 |
-
"eval_steps_per_second": 1.97,
|
| 749 |
-
"step": 500
|
| 750 |
-
},
|
| 751 |
-
{
|
| 752 |
-
"epoch": 1.5482388973966308,
|
| 753 |
-
"grad_norm": 0.6826627810241662,
|
| 754 |
-
"learning_rate": 1.7435745567042096e-05,
|
| 755 |
-
"loss": 0.7871,
|
| 756 |
-
"step": 505
|
| 757 |
-
},
|
| 758 |
-
{
|
| 759 |
-
"epoch": 1.5635528330781012,
|
| 760 |
-
"grad_norm": 0.7329202799692207,
|
| 761 |
-
"learning_rate": 1.7363724379236237e-05,
|
| 762 |
-
"loss": 0.806,
|
| 763 |
-
"step": 510
|
| 764 |
-
},
|
| 765 |
-
{
|
| 766 |
-
"epoch": 1.5788667687595712,
|
| 767 |
-
"grad_norm": 0.8605855369920612,
|
| 768 |
-
"learning_rate": 1.7290858937868296e-05,
|
| 769 |
-
"loss": 0.8134,
|
| 770 |
-
"step": 515
|
| 771 |
-
},
|
| 772 |
-
{
|
| 773 |
-
"epoch": 1.5941807044410412,
|
| 774 |
-
"grad_norm": 0.6963610579257828,
|
| 775 |
-
"learning_rate": 1.7217157596986474e-05,
|
| 776 |
-
"loss": 0.8057,
|
| 777 |
-
"step": 520
|
| 778 |
-
},
|
| 779 |
-
{
|
| 780 |
-
"epoch": 1.6094946401225116,
|
| 781 |
-
"grad_norm": 0.715201778907277,
|
| 782 |
-
"learning_rate": 1.7142628806475144e-05,
|
| 783 |
-
"loss": 0.806,
|
| 784 |
-
"step": 525
|
| 785 |
-
},
|
| 786 |
-
{
|
| 787 |
-
"epoch": 1.6248085758039816,
|
| 788 |
-
"grad_norm": 0.7191782284781755,
|
| 789 |
-
"learning_rate": 1.706728111108607e-05,
|
| 790 |
-
"loss": 0.8027,
|
| 791 |
-
"step": 530
|
| 792 |
-
},
|
| 793 |
-
{
|
| 794 |
-
"epoch": 1.6401225114854516,
|
| 795 |
-
"grad_norm": 0.6872215034145709,
|
| 796 |
-
"learning_rate": 1.699112314945874e-05,
|
| 797 |
-
"loss": 0.7953,
|
| 798 |
-
"step": 535
|
| 799 |
-
},
|
| 800 |
-
{
|
| 801 |
-
"epoch": 1.655436447166922,
|
| 802 |
-
"grad_norm": 0.7008995671254957,
|
| 803 |
-
"learning_rate": 1.691416365312996e-05,
|
| 804 |
-
"loss": 0.8096,
|
| 805 |
-
"step": 540
|
| 806 |
-
},
|
| 807 |
-
{
|
| 808 |
-
"epoch": 1.670750382848392,
|
| 809 |
-
"grad_norm": 0.6521306963395784,
|
| 810 |
-
"learning_rate": 1.683641144553275e-05,
|
| 811 |
-
"loss": 0.7921,
|
| 812 |
-
"step": 545
|
| 813 |
-
},
|
| 814 |
-
{
|
| 815 |
-
"epoch": 1.686064318529862,
|
| 816 |
-
"grad_norm": 0.6632532080286483,
|
| 817 |
-
"learning_rate": 1.675787544098477e-05,
|
| 818 |
-
"loss": 0.8056,
|
| 819 |
-
"step": 550
|
| 820 |
-
},
|
| 821 |
-
{
|
| 822 |
-
"epoch": 1.7013782542113323,
|
| 823 |
-
"grad_norm": 0.6547969582532698,
|
| 824 |
-
"learning_rate": 1.667856464366626e-05,
|
| 825 |
-
"loss": 0.7819,
|
| 826 |
-
"step": 555
|
| 827 |
-
},
|
| 828 |
-
{
|
| 829 |
-
"epoch": 1.7166921898928025,
|
| 830 |
-
"grad_norm": 0.7046901763937415,
|
| 831 |
-
"learning_rate": 1.6598488146587733e-05,
|
| 832 |
-
"loss": 0.8061,
|
| 833 |
-
"step": 560
|
| 834 |
-
},
|
| 835 |
-
{
|
| 836 |
-
"epoch": 1.7320061255742725,
|
| 837 |
-
"grad_norm": 0.6788820639858653,
|
| 838 |
-
"learning_rate": 1.6517655130547435e-05,
|
| 839 |
-
"loss": 0.7997,
|
| 840 |
-
"step": 565
|
| 841 |
-
},
|
| 842 |
-
{
|
| 843 |
-
"epoch": 1.7473200612557427,
|
| 844 |
-
"grad_norm": 0.6894021837769623,
|
| 845 |
-
"learning_rate": 1.6436074863078783e-05,
|
| 846 |
-
"loss": 0.803,
|
| 847 |
-
"step": 570
|
| 848 |
-
},
|
| 849 |
-
{
|
| 850 |
-
"epoch": 1.762633996937213,
|
| 851 |
-
"grad_norm": 0.7360294460315284,
|
| 852 |
-
"learning_rate": 1.635375669738782e-05,
|
| 853 |
-
"loss": 0.7975,
|
| 854 |
-
"step": 575
|
| 855 |
-
},
|
| 856 |
-
{
|
| 857 |
-
"epoch": 1.777947932618683,
|
| 858 |
-
"grad_norm": 0.6850098881910617,
|
| 859 |
-
"learning_rate": 1.627071007128089e-05,
|
| 860 |
-
"loss": 0.7825,
|
| 861 |
-
"step": 580
|
| 862 |
-
},
|
| 863 |
-
{
|
| 864 |
-
"epoch": 1.793261868300153,
|
| 865 |
-
"grad_norm": 0.7278655150611072,
|
| 866 |
-
"learning_rate": 1.618694450608256e-05,
|
| 867 |
-
"loss": 0.7955,
|
| 868 |
-
"step": 585
|
| 869 |
-
},
|
| 870 |
-
{
|
| 871 |
-
"epoch": 1.8085758039816233,
|
| 872 |
-
"grad_norm": 0.7122173514963583,
|
| 873 |
-
"learning_rate": 1.6102469605544036e-05,
|
| 874 |
-
"loss": 0.808,
|
| 875 |
-
"step": 590
|
| 876 |
-
},
|
| 877 |
-
{
|
| 878 |
-
"epoch": 1.8238897396630933,
|
| 879 |
-
"grad_norm": 0.6925118679066572,
|
| 880 |
-
"learning_rate": 1.6017295054742045e-05,
|
| 881 |
-
"loss": 0.7875,
|
| 882 |
-
"step": 595
|
| 883 |
-
},
|
| 884 |
-
{
|
| 885 |
-
"epoch": 1.8392036753445635,
|
| 886 |
-
"grad_norm": 0.6857769438421079,
|
| 887 |
-
"learning_rate": 1.5931430618968476e-05,
|
| 888 |
-
"loss": 0.7884,
|
| 889 |
-
"step": 600
|
| 890 |
-
},
|
| 891 |
-
{
|
| 892 |
-
"epoch": 1.8392036753445635,
|
| 893 |
-
"eval_loss": 0.8516013622283936,
|
| 894 |
-
"eval_runtime": 4.2451,
|
| 895 |
-
"eval_samples_per_second": 29.21,
|
| 896 |
-
"eval_steps_per_second": 1.885,
|
| 897 |
-
"step": 600
|
| 898 |
-
},
|
| 899 |
-
{
|
| 900 |
-
"epoch": 1.8545176110260337,
|
| 901 |
-
"grad_norm": 0.6326947636704211,
|
| 902 |
-
"learning_rate": 1.5844886142610763e-05,
|
| 903 |
-
"loss": 0.7819,
|
| 904 |
-
"step": 605
|
| 905 |
-
},
|
| 906 |
-
{
|
| 907 |
-
"epoch": 1.8698315467075037,
|
| 908 |
-
"grad_norm": 0.666694114425699,
|
| 909 |
-
"learning_rate": 1.575767154802323e-05,
|
| 910 |
-
"loss": 0.7777,
|
| 911 |
-
"step": 610
|
| 912 |
-
},
|
| 913 |
-
{
|
| 914 |
-
"epoch": 1.885145482388974,
|
| 915 |
-
"grad_norm": 0.6182711467351976,
|
| 916 |
-
"learning_rate": 1.5669796834389496e-05,
|
| 917 |
-
"loss": 0.7889,
|
| 918 |
-
"step": 615
|
| 919 |
-
},
|
| 920 |
-
{
|
| 921 |
-
"epoch": 1.9004594180704442,
|
| 922 |
-
"grad_norm": 0.6402744830423595,
|
| 923 |
-
"learning_rate": 1.5581272076576047e-05,
|
| 924 |
-
"loss": 0.7839,
|
| 925 |
-
"step": 620
|
| 926 |
-
},
|
| 927 |
-
{
|
| 928 |
-
"epoch": 1.9157733537519142,
|
| 929 |
-
"grad_norm": 0.6612456968952057,
|
| 930 |
-
"learning_rate": 1.5492107423977167e-05,
|
| 931 |
-
"loss": 0.7884,
|
| 932 |
-
"step": 625
|
| 933 |
-
},
|
| 934 |
-
{
|
| 935 |
-
"epoch": 1.9310872894333844,
|
| 936 |
-
"grad_norm": 0.6757984187665057,
|
| 937 |
-
"learning_rate": 1.5402313099351302e-05,
|
| 938 |
-
"loss": 0.7784,
|
| 939 |
-
"step": 630
|
| 940 |
-
},
|
| 941 |
-
{
|
| 942 |
-
"epoch": 1.9464012251148546,
|
| 943 |
-
"grad_norm": 0.6707442527908725,
|
| 944 |
-
"learning_rate": 1.5311899397649e-05,
|
| 945 |
-
"loss": 0.7935,
|
| 946 |
-
"step": 635
|
| 947 |
-
},
|
| 948 |
-
{
|
| 949 |
-
"epoch": 1.9617151607963246,
|
| 950 |
-
"grad_norm": 0.787792189502549,
|
| 951 |
-
"learning_rate": 1.522087668483264e-05,
|
| 952 |
-
"loss": 0.779,
|
| 953 |
-
"step": 640
|
| 954 |
-
},
|
| 955 |
-
{
|
| 956 |
-
"epoch": 1.9770290964777948,
|
| 957 |
-
"grad_norm": 0.6925473058613637,
|
| 958 |
-
"learning_rate": 1.5129255396687899e-05,
|
| 959 |
-
"loss": 0.7891,
|
| 960 |
-
"step": 645
|
| 961 |
-
},
|
| 962 |
-
{
|
| 963 |
-
"epoch": 1.992343032159265,
|
| 964 |
-
"grad_norm": 0.6890667970589922,
|
| 965 |
-
"learning_rate": 1.503704603762734e-05,
|
| 966 |
-
"loss": 0.7693,
|
| 967 |
-
"step": 650
|
| 968 |
-
},
|
| 969 |
-
{
|
| 970 |
-
"epoch": 2.009188361408882,
|
| 971 |
-
"grad_norm": 0.8106643045129424,
|
| 972 |
-
"learning_rate": 1.4944259179486068e-05,
|
| 973 |
-
"loss": 0.9039,
|
| 974 |
-
"step": 655
|
| 975 |
-
},
|
| 976 |
-
{
|
| 977 |
-
"epoch": 2.0245022970903523,
|
| 978 |
-
"grad_norm": 0.7728005094053498,
|
| 979 |
-
"learning_rate": 1.4850905460309648e-05,
|
| 980 |
-
"loss": 0.7116,
|
| 981 |
-
"step": 660
|
| 982 |
-
},
|
| 983 |
-
{
|
| 984 |
-
"epoch": 2.0398162327718223,
|
| 985 |
-
"grad_norm": 0.7301328106464207,
|
| 986 |
-
"learning_rate": 1.4756995583134463e-05,
|
| 987 |
-
"loss": 0.7313,
|
| 988 |
-
"step": 665
|
| 989 |
-
},
|
| 990 |
-
{
|
| 991 |
-
"epoch": 2.0551301684532923,
|
| 992 |
-
"grad_norm": 0.702048383564715,
|
| 993 |
-
"learning_rate": 1.4662540314760608e-05,
|
| 994 |
-
"loss": 0.7222,
|
| 995 |
-
"step": 670
|
| 996 |
-
},
|
| 997 |
-
{
|
| 998 |
-
"epoch": 2.0704441041347628,
|
| 999 |
-
"grad_norm": 0.7081084536553046,
|
| 1000 |
-
"learning_rate": 1.4567550484517456e-05,
|
| 1001 |
-
"loss": 0.7214,
|
| 1002 |
-
"step": 675
|
| 1003 |
-
},
|
| 1004 |
-
{
|
| 1005 |
-
"epoch": 2.0857580398162328,
|
| 1006 |
-
"grad_norm": 0.7492389283409402,
|
| 1007 |
-
"learning_rate": 1.4472036983022106e-05,
|
| 1008 |
-
"loss": 0.7251,
|
| 1009 |
-
"step": 680
|
| 1010 |
-
},
|
| 1011 |
-
{
|
| 1012 |
-
"epoch": 2.1010719754977027,
|
| 1013 |
-
"grad_norm": 0.7183839129962212,
|
| 1014 |
-
"learning_rate": 1.437601076093073e-05,
|
| 1015 |
-
"loss": 0.71,
|
| 1016 |
-
"step": 685
|
| 1017 |
-
},
|
| 1018 |
-
{
|
| 1019 |
-
"epoch": 2.116385911179173,
|
| 1020 |
-
"grad_norm": 0.6904647110507196,
|
| 1021 |
-
"learning_rate": 1.4279482827683095e-05,
|
| 1022 |
-
"loss": 0.724,
|
| 1023 |
-
"step": 690
|
| 1024 |
-
},
|
| 1025 |
-
{
|
| 1026 |
-
"epoch": 2.131699846860643,
|
| 1027 |
-
"grad_norm": 0.6745352346306862,
|
| 1028 |
-
"learning_rate": 1.4182464250240341e-05,
|
| 1029 |
-
"loss": 0.7127,
|
| 1030 |
-
"step": 695
|
| 1031 |
-
},
|
| 1032 |
-
{
|
| 1033 |
-
"epoch": 2.147013782542113,
|
| 1034 |
-
"grad_norm": 0.7254396412798532,
|
| 1035 |
-
"learning_rate": 1.4084966151816124e-05,
|
| 1036 |
-
"loss": 0.7071,
|
| 1037 |
-
"step": 700
|
| 1038 |
-
},
|
| 1039 |
-
{
|
| 1040 |
-
"epoch": 2.147013782542113,
|
| 1041 |
-
"eval_loss": 0.8550077676773071,
|
| 1042 |
-
"eval_runtime": 3.8848,
|
| 1043 |
-
"eval_samples_per_second": 31.919,
|
| 1044 |
-
"eval_steps_per_second": 2.059,
|
| 1045 |
-
"step": 700
|
| 1046 |
-
},
|
| 1047 |
-
{
|
| 1048 |
-
"epoch": 2.1623277182235836,
|
| 1049 |
-
"grad_norm": 0.73349139216254,
|
| 1050 |
-
"learning_rate": 1.3986999710601348e-05,
|
| 1051 |
-
"loss": 0.7298,
|
| 1052 |
-
"step": 705
|
| 1053 |
-
},
|
| 1054 |
-
{
|
| 1055 |
-
"epoch": 2.1776416539050536,
|
| 1056 |
-
"grad_norm": 0.6655753573647281,
|
| 1057 |
-
"learning_rate": 1.3888576158482586e-05,
|
| 1058 |
-
"loss": 0.7124,
|
| 1059 |
-
"step": 710
|
| 1060 |
-
},
|
| 1061 |
-
{
|
| 1062 |
-
"epoch": 2.1929555895865236,
|
| 1063 |
-
"grad_norm": 0.6987464871327375,
|
| 1064 |
-
"learning_rate": 1.3789706779754326e-05,
|
| 1065 |
-
"loss": 0.712,
|
| 1066 |
-
"step": 715
|
| 1067 |
-
},
|
| 1068 |
-
{
|
| 1069 |
-
"epoch": 2.208269525267994,
|
| 1070 |
-
"grad_norm": 0.7104463485359258,
|
| 1071 |
-
"learning_rate": 1.3690402909825245e-05,
|
| 1072 |
-
"loss": 0.7256,
|
| 1073 |
-
"step": 720
|
| 1074 |
-
},
|
| 1075 |
-
{
|
| 1076 |
-
"epoch": 2.223583460949464,
|
| 1077 |
-
"grad_norm": 0.786597658435966,
|
| 1078 |
-
"learning_rate": 1.3590675933918578e-05,
|
| 1079 |
-
"loss": 0.7265,
|
| 1080 |
-
"step": 725
|
| 1081 |
-
},
|
| 1082 |
-
{
|
| 1083 |
-
"epoch": 2.238897396630934,
|
| 1084 |
-
"grad_norm": 0.7359585689347169,
|
| 1085 |
-
"learning_rate": 1.3490537285766809e-05,
|
| 1086 |
-
"loss": 0.7167,
|
| 1087 |
-
"step": 730
|
| 1088 |
-
},
|
| 1089 |
-
{
|
| 1090 |
-
"epoch": 2.2542113323124044,
|
| 1091 |
-
"grad_norm": 0.6905264840508457,
|
| 1092 |
-
"learning_rate": 1.3389998446300791e-05,
|
| 1093 |
-
"loss": 0.7046,
|
| 1094 |
-
"step": 735
|
| 1095 |
-
},
|
| 1096 |
-
{
|
| 1097 |
-
"epoch": 2.2695252679938744,
|
| 1098 |
-
"grad_norm": 0.7110824744193723,
|
| 1099 |
-
"learning_rate": 1.3289070942333448e-05,
|
| 1100 |
-
"loss": 0.7113,
|
| 1101 |
-
"step": 740
|
| 1102 |
-
},
|
| 1103 |
-
{
|
| 1104 |
-
"epoch": 2.2848392036753444,
|
| 1105 |
-
"grad_norm": 0.774570053362907,
|
| 1106 |
-
"learning_rate": 1.3187766345238222e-05,
|
| 1107 |
-
"loss": 0.7097,
|
| 1108 |
-
"step": 745
|
| 1109 |
-
},
|
| 1110 |
-
{
|
| 1111 |
-
"epoch": 2.300153139356815,
|
| 1112 |
-
"grad_norm": 0.7178949231829396,
|
| 1113 |
-
"learning_rate": 1.308609626962242e-05,
|
| 1114 |
-
"loss": 0.6951,
|
| 1115 |
-
"step": 750
|
| 1116 |
-
},
|
| 1117 |
-
{
|
| 1118 |
-
"epoch": 2.315467075038285,
|
| 1119 |
-
"grad_norm": 0.6778307950742112,
|
| 1120 |
-
"learning_rate": 1.2984072371995581e-05,
|
| 1121 |
-
"loss": 0.7119,
|
| 1122 |
-
"step": 755
|
| 1123 |
-
},
|
| 1124 |
-
{
|
| 1125 |
-
"epoch": 2.330781010719755,
|
| 1126 |
-
"grad_norm": 0.7381317901698428,
|
| 1127 |
-
"learning_rate": 1.288170634943307e-05,
|
| 1128 |
-
"loss": 0.7179,
|
| 1129 |
-
"step": 760
|
| 1130 |
-
},
|
| 1131 |
-
{
|
| 1132 |
-
"epoch": 2.3460949464012253,
|
| 1133 |
-
"grad_norm": 0.688339196574423,
|
| 1134 |
-
"learning_rate": 1.2779009938234986e-05,
|
| 1135 |
-
"loss": 0.7372,
|
| 1136 |
-
"step": 765
|
| 1137 |
-
},
|
| 1138 |
-
{
|
| 1139 |
-
"epoch": 2.3614088820826953,
|
| 1140 |
-
"grad_norm": 0.7309911889901869,
|
| 1141 |
-
"learning_rate": 1.2675994912580601e-05,
|
| 1142 |
-
"loss": 0.7217,
|
| 1143 |
-
"step": 770
|
| 1144 |
-
},
|
| 1145 |
-
{
|
| 1146 |
-
"epoch": 2.3767228177641653,
|
| 1147 |
-
"grad_norm": 2.627453466768546,
|
| 1148 |
-
"learning_rate": 1.2572673083178448e-05,
|
| 1149 |
-
"loss": 0.7208,
|
| 1150 |
-
"step": 775
|
| 1151 |
-
},
|
| 1152 |
-
{
|
| 1153 |
-
"epoch": 2.3920367534456357,
|
| 1154 |
-
"grad_norm": 0.6825595176377366,
|
| 1155 |
-
"learning_rate": 1.2469056295912216e-05,
|
| 1156 |
-
"loss": 0.7173,
|
| 1157 |
-
"step": 780
|
| 1158 |
-
},
|
| 1159 |
-
{
|
| 1160 |
-
"epoch": 2.4073506891271057,
|
| 1161 |
-
"grad_norm": 0.681764187496552,
|
| 1162 |
-
"learning_rate": 1.2365156430482621e-05,
|
| 1163 |
-
"loss": 0.7172,
|
| 1164 |
-
"step": 785
|
| 1165 |
-
},
|
| 1166 |
-
{
|
| 1167 |
-
"epoch": 2.4226646248085757,
|
| 1168 |
-
"grad_norm": 0.6957949104606218,
|
| 1169 |
-
"learning_rate": 1.2260985399045379e-05,
|
| 1170 |
-
"loss": 0.7144,
|
| 1171 |
-
"step": 790
|
| 1172 |
-
},
|
| 1173 |
-
{
|
| 1174 |
-
"epoch": 2.437978560490046,
|
| 1175 |
-
"grad_norm": 0.6810069800053375,
|
| 1176 |
-
"learning_rate": 1.2156555144845489e-05,
|
| 1177 |
-
"loss": 0.7153,
|
| 1178 |
-
"step": 795
|
| 1179 |
-
},
|
| 1180 |
-
{
|
| 1181 |
-
"epoch": 2.453292496171516,
|
| 1182 |
-
"grad_norm": 0.6879227501131829,
|
| 1183 |
-
"learning_rate": 1.2051877640847929e-05,
|
| 1184 |
-
"loss": 0.7208,
|
| 1185 |
-
"step": 800
|
| 1186 |
-
},
|
| 1187 |
-
{
|
| 1188 |
-
"epoch": 2.453292496171516,
|
| 1189 |
-
"eval_loss": 0.8501381278038025,
|
| 1190 |
-
"eval_runtime": 3.7489,
|
| 1191 |
-
"eval_samples_per_second": 33.076,
|
| 1192 |
-
"eval_steps_per_second": 2.134,
|
| 1193 |
-
"step": 800
|
| 1194 |
-
},
|
| 1195 |
-
{
|
| 1196 |
-
"epoch": 2.468606431852986,
|
| 1197 |
-
"grad_norm": 0.7074177591745171,
|
| 1198 |
-
"learning_rate": 1.1946964888364949e-05,
|
| 1199 |
-
"loss": 0.7293,
|
| 1200 |
-
"step": 805
|
| 1201 |
-
},
|
| 1202 |
-
{
|
| 1203 |
-
"epoch": 2.4839203675344566,
|
| 1204 |
-
"grad_norm": 0.7100957198483567,
|
| 1205 |
-
"learning_rate": 1.1841828915680127e-05,
|
| 1206 |
-
"loss": 0.7088,
|
| 1207 |
-
"step": 810
|
| 1208 |
-
},
|
| 1209 |
-
{
|
| 1210 |
-
"epoch": 2.4992343032159265,
|
| 1211 |
-
"grad_norm": 0.7065376294005609,
|
| 1212 |
-
"learning_rate": 1.1736481776669307e-05,
|
| 1213 |
-
"loss": 0.7083,
|
| 1214 |
-
"step": 815
|
| 1215 |
-
},
|
| 1216 |
-
{
|
| 1217 |
-
"epoch": 2.5145482388973965,
|
| 1218 |
-
"grad_norm": 0.699699294689246,
|
| 1219 |
-
"learning_rate": 1.1630935549418627e-05,
|
| 1220 |
-
"loss": 0.7239,
|
| 1221 |
-
"step": 820
|
| 1222 |
-
},
|
| 1223 |
-
{
|
| 1224 |
-
"epoch": 2.5298621745788665,
|
| 1225 |
-
"grad_norm": 0.6931742613638052,
|
| 1226 |
-
"learning_rate": 1.1525202334839771e-05,
|
| 1227 |
-
"loss": 0.7257,
|
| 1228 |
-
"step": 825
|
| 1229 |
-
},
|
| 1230 |
-
{
|
| 1231 |
-
"epoch": 2.545176110260337,
|
| 1232 |
-
"grad_norm": 0.6626821835687099,
|
| 1233 |
-
"learning_rate": 1.1419294255282574e-05,
|
| 1234 |
-
"loss": 0.7158,
|
| 1235 |
-
"step": 830
|
| 1236 |
-
},
|
| 1237 |
-
{
|
| 1238 |
-
"epoch": 2.560490045941807,
|
| 1239 |
-
"grad_norm": 0.7476424454423357,
|
| 1240 |
-
"learning_rate": 1.1313223453145202e-05,
|
| 1241 |
-
"loss": 0.7231,
|
| 1242 |
-
"step": 835
|
| 1243 |
-
},
|
| 1244 |
-
{
|
| 1245 |
-
"epoch": 2.5758039816232774,
|
| 1246 |
-
"grad_norm": 0.7121987313639168,
|
| 1247 |
-
"learning_rate": 1.1207002089482026e-05,
|
| 1248 |
-
"loss": 0.7272,
|
| 1249 |
-
"step": 840
|
| 1250 |
-
},
|
| 1251 |
-
{
|
| 1252 |
-
"epoch": 2.5911179173047474,
|
| 1253 |
-
"grad_norm": 0.6842806839970864,
|
| 1254 |
-
"learning_rate": 1.1100642342609352e-05,
|
| 1255 |
-
"loss": 0.7215,
|
| 1256 |
-
"step": 845
|
| 1257 |
-
},
|
| 1258 |
-
{
|
| 1259 |
-
"epoch": 2.6064318529862174,
|
| 1260 |
-
"grad_norm": 0.671282856198737,
|
| 1261 |
-
"learning_rate": 1.0994156406709155e-05,
|
| 1262 |
-
"loss": 0.7086,
|
| 1263 |
-
"step": 850
|
| 1264 |
-
},
|
| 1265 |
-
{
|
| 1266 |
-
"epoch": 2.6217457886676874,
|
| 1267 |
-
"grad_norm": 0.7127796423271462,
|
| 1268 |
-
"learning_rate": 1.088755649043104e-05,
|
| 1269 |
-
"loss": 0.7113,
|
| 1270 |
-
"step": 855
|
| 1271 |
-
},
|
| 1272 |
-
{
|
| 1273 |
-
"epoch": 2.637059724349158,
|
| 1274 |
-
"grad_norm": 0.6642491628332302,
|
| 1275 |
-
"learning_rate": 1.0780854815492496e-05,
|
| 1276 |
-
"loss": 0.7247,
|
| 1277 |
-
"step": 860
|
| 1278 |
-
},
|
| 1279 |
-
{
|
| 1280 |
-
"epoch": 2.652373660030628,
|
| 1281 |
-
"grad_norm": 0.6698942933482407,
|
| 1282 |
-
"learning_rate": 1.0674063615277681e-05,
|
| 1283 |
-
"loss": 0.7301,
|
| 1284 |
-
"step": 865
|
| 1285 |
-
},
|
| 1286 |
-
{
|
| 1287 |
-
"epoch": 2.6676875957120982,
|
| 1288 |
-
"grad_norm": 0.6690575090698347,
|
| 1289 |
-
"learning_rate": 1.0567195133434851e-05,
|
| 1290 |
-
"loss": 0.7318,
|
| 1291 |
-
"step": 870
|
| 1292 |
-
},
|
| 1293 |
-
{
|
| 1294 |
-
"epoch": 2.6830015313935682,
|
| 1295 |
-
"grad_norm": 0.6647266330654462,
|
| 1296 |
-
"learning_rate": 1.0460261622472631e-05,
|
| 1297 |
-
"loss": 0.7143,
|
| 1298 |
-
"step": 875
|
| 1299 |
-
},
|
| 1300 |
-
{
|
| 1301 |
-
"epoch": 2.698315467075038,
|
| 1302 |
-
"grad_norm": 0.6879144621587469,
|
| 1303 |
-
"learning_rate": 1.0353275342355262e-05,
|
| 1304 |
-
"loss": 0.7227,
|
| 1305 |
-
"step": 880
|
| 1306 |
-
},
|
| 1307 |
-
{
|
| 1308 |
-
"epoch": 2.713629402756508,
|
| 1309 |
-
"grad_norm": 0.6775051673571305,
|
| 1310 |
-
"learning_rate": 1.024624855909698e-05,
|
| 1311 |
-
"loss": 0.715,
|
| 1312 |
-
"step": 885
|
| 1313 |
-
},
|
| 1314 |
-
{
|
| 1315 |
-
"epoch": 2.7289433384379786,
|
| 1316 |
-
"grad_norm": 0.6785052740842338,
|
| 1317 |
-
"learning_rate": 1.013919354335572e-05,
|
| 1318 |
-
"loss": 0.7224,
|
| 1319 |
-
"step": 890
|
| 1320 |
-
},
|
| 1321 |
-
{
|
| 1322 |
-
"epoch": 2.7442572741194486,
|
| 1323 |
-
"grad_norm": 0.6852717568024729,
|
| 1324 |
-
"learning_rate": 1.0032122569026284e-05,
|
| 1325 |
-
"loss": 0.7181,
|
| 1326 |
-
"step": 895
|
| 1327 |
-
},
|
| 1328 |
-
{
|
| 1329 |
-
"epoch": 2.759571209800919,
|
| 1330 |
-
"grad_norm": 0.6966758449578118,
|
| 1331 |
-
"learning_rate": 9.925047911833137e-06,
|
| 1332 |
-
"loss": 0.726,
|
| 1333 |
-
"step": 900
|
| 1334 |
-
},
|
| 1335 |
-
{
|
| 1336 |
-
"epoch": 2.759571209800919,
|
| 1337 |
-
"eval_loss": 0.8449206352233887,
|
| 1338 |
-
"eval_runtime": 3.7457,
|
| 1339 |
-
"eval_samples_per_second": 33.104,
|
| 1340 |
-
"eval_steps_per_second": 2.136,
|
| 1341 |
-
"step": 900
|
| 1342 |
-
}
|
| 1343 |
-
],
|
| 1344 |
-
"logging_steps": 5,
|
| 1345 |
-
"max_steps": 1630,
|
| 1346 |
-
"num_input_tokens_seen": 0,
|
| 1347 |
-
"num_train_epochs": 5,
|
| 1348 |
-
"save_steps": 100,
|
| 1349 |
-
"stateful_callbacks": {
|
| 1350 |
-
"TrainerControl": {
|
| 1351 |
-
"args": {
|
| 1352 |
-
"should_epoch_stop": false,
|
| 1353 |
-
"should_evaluate": false,
|
| 1354 |
-
"should_log": false,
|
| 1355 |
-
"should_save": true,
|
| 1356 |
-
"should_training_stop": false
|
| 1357 |
-
},
|
| 1358 |
-
"attributes": {}
|
| 1359 |
-
}
|
| 1360 |
-
},
|
| 1361 |
-
"total_flos": 95696971628544.0,
|
| 1362 |
-
"train_batch_size": 4,
|
| 1363 |
-
"trial_name": null,
|
| 1364 |
-
"trial_params": null
|
| 1365 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:8128bba117ecebe610aa8a93374390d0c029e4632d49ee23fa1bd8e6b39d6679
|
| 3 |
-
size 7352
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-900/zero_to_fp32.py
DELETED
|
@@ -1,674 +0,0 @@
|
|
| 1 |
-
#!/usr/bin/env python
|
| 2 |
-
|
| 3 |
-
# Copyright (c) Microsoft Corporation.
|
| 4 |
-
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
-
|
| 6 |
-
# DeepSpeed Team
|
| 7 |
-
|
| 8 |
-
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
-
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
-
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
-
# application.
|
| 12 |
-
#
|
| 13 |
-
# example:
|
| 14 |
-
# python zero_to_fp32.py . output_dir/
|
| 15 |
-
# or
|
| 16 |
-
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
| 17 |
-
|
| 18 |
-
import argparse
|
| 19 |
-
import torch
|
| 20 |
-
import glob
|
| 21 |
-
import math
|
| 22 |
-
import os
|
| 23 |
-
import re
|
| 24 |
-
import json
|
| 25 |
-
from tqdm import tqdm
|
| 26 |
-
from collections import OrderedDict
|
| 27 |
-
from dataclasses import dataclass
|
| 28 |
-
|
| 29 |
-
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 30 |
-
# DeepSpeed data structures it has to be available in the current python environment.
|
| 31 |
-
from deepspeed.utils import logger
|
| 32 |
-
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 33 |
-
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 34 |
-
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
@dataclass
|
| 38 |
-
class zero_model_state:
|
| 39 |
-
buffers: dict()
|
| 40 |
-
param_shapes: dict()
|
| 41 |
-
shared_params: list
|
| 42 |
-
ds_version: int
|
| 43 |
-
frozen_param_shapes: dict()
|
| 44 |
-
frozen_param_fragments: dict()
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
debug = 0
|
| 48 |
-
|
| 49 |
-
# load to cpu
|
| 50 |
-
device = torch.device('cpu')
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
def atoi(text):
|
| 54 |
-
return int(text) if text.isdigit() else text
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
def natural_keys(text):
|
| 58 |
-
'''
|
| 59 |
-
alist.sort(key=natural_keys) sorts in human order
|
| 60 |
-
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 61 |
-
(See Toothy's implementation in the comments)
|
| 62 |
-
'''
|
| 63 |
-
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 67 |
-
if not os.path.isdir(checkpoint_dir):
|
| 68 |
-
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 69 |
-
|
| 70 |
-
# there should be only one file
|
| 71 |
-
if zero_stage <= 2:
|
| 72 |
-
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 73 |
-
elif zero_stage == 3:
|
| 74 |
-
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 75 |
-
|
| 76 |
-
if not os.path.exists(file):
|
| 77 |
-
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 78 |
-
|
| 79 |
-
return file
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 83 |
-
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 84 |
-
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 85 |
-
|
| 86 |
-
if len(ckpt_files) == 0:
|
| 87 |
-
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 88 |
-
|
| 89 |
-
return ckpt_files
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
def get_optim_files(checkpoint_dir):
|
| 93 |
-
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 94 |
-
|
| 95 |
-
|
| 96 |
-
def get_model_state_files(checkpoint_dir):
|
| 97 |
-
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 98 |
-
|
| 99 |
-
|
| 100 |
-
def parse_model_states(files):
|
| 101 |
-
zero_model_states = []
|
| 102 |
-
for file in files:
|
| 103 |
-
state_dict = torch.load(file, map_location=device)
|
| 104 |
-
|
| 105 |
-
if BUFFER_NAMES not in state_dict:
|
| 106 |
-
raise ValueError(f"{file} is not a model state checkpoint")
|
| 107 |
-
buffer_names = state_dict[BUFFER_NAMES]
|
| 108 |
-
if debug:
|
| 109 |
-
print("Found buffers:", buffer_names)
|
| 110 |
-
|
| 111 |
-
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 112 |
-
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 113 |
-
param_shapes = state_dict[PARAM_SHAPES]
|
| 114 |
-
|
| 115 |
-
# collect parameters that are included in param_shapes
|
| 116 |
-
param_names = []
|
| 117 |
-
for s in param_shapes:
|
| 118 |
-
for name in s.keys():
|
| 119 |
-
param_names.append(name)
|
| 120 |
-
|
| 121 |
-
# update with frozen parameters
|
| 122 |
-
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 123 |
-
if frozen_param_shapes is not None:
|
| 124 |
-
if debug:
|
| 125 |
-
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 126 |
-
param_names += list(frozen_param_shapes.keys())
|
| 127 |
-
|
| 128 |
-
# handle shared params
|
| 129 |
-
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 130 |
-
|
| 131 |
-
ds_version = state_dict.get(DS_VERSION, None)
|
| 132 |
-
|
| 133 |
-
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 134 |
-
|
| 135 |
-
z_model_state = zero_model_state(buffers=buffers,
|
| 136 |
-
param_shapes=param_shapes,
|
| 137 |
-
shared_params=shared_params,
|
| 138 |
-
ds_version=ds_version,
|
| 139 |
-
frozen_param_shapes=frozen_param_shapes,
|
| 140 |
-
frozen_param_fragments=frozen_param_fragments)
|
| 141 |
-
zero_model_states.append(z_model_state)
|
| 142 |
-
|
| 143 |
-
return zero_model_states
|
| 144 |
-
|
| 145 |
-
|
| 146 |
-
def parse_optim_states(files, ds_checkpoint_dir):
|
| 147 |
-
total_files = len(files)
|
| 148 |
-
state_dicts = []
|
| 149 |
-
for f in files:
|
| 150 |
-
state_dict = torch.load(f, map_location=device)
|
| 151 |
-
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
| 152 |
-
# and also handle the case where it was already removed by another helper script
|
| 153 |
-
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
| 154 |
-
state_dicts.append(state_dict)
|
| 155 |
-
|
| 156 |
-
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 157 |
-
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 158 |
-
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 159 |
-
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 160 |
-
|
| 161 |
-
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 162 |
-
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 163 |
-
# use the max of the partition_count to get the dp world_size.
|
| 164 |
-
|
| 165 |
-
if type(world_size) is list:
|
| 166 |
-
world_size = max(world_size)
|
| 167 |
-
|
| 168 |
-
if world_size != total_files:
|
| 169 |
-
raise ValueError(
|
| 170 |
-
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 171 |
-
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 172 |
-
)
|
| 173 |
-
|
| 174 |
-
# the groups are named differently in each stage
|
| 175 |
-
if zero_stage <= 2:
|
| 176 |
-
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 177 |
-
elif zero_stage == 3:
|
| 178 |
-
fp32_groups_key = FP32_FLAT_GROUPS
|
| 179 |
-
else:
|
| 180 |
-
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 181 |
-
|
| 182 |
-
if zero_stage <= 2:
|
| 183 |
-
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 184 |
-
elif zero_stage == 3:
|
| 185 |
-
# if there is more than one param group, there will be multiple flattened tensors - one
|
| 186 |
-
# flattened tensor per group - for simplicity merge them into a single tensor
|
| 187 |
-
#
|
| 188 |
-
# XXX: could make the script more memory efficient for when there are multiple groups - it
|
| 189 |
-
# will require matching the sub-lists of param_shapes for each param group flattened tensor
|
| 190 |
-
|
| 191 |
-
fp32_flat_groups = [
|
| 192 |
-
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
|
| 193 |
-
]
|
| 194 |
-
|
| 195 |
-
return zero_stage, world_size, fp32_flat_groups
|
| 196 |
-
|
| 197 |
-
|
| 198 |
-
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
| 199 |
-
"""
|
| 200 |
-
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 201 |
-
|
| 202 |
-
Args:
|
| 203 |
-
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 204 |
-
|
| 205 |
-
"""
|
| 206 |
-
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 207 |
-
|
| 208 |
-
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 209 |
-
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 210 |
-
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 211 |
-
|
| 212 |
-
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 213 |
-
|
| 214 |
-
zero_model_states = parse_model_states(model_files)
|
| 215 |
-
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 216 |
-
|
| 217 |
-
if zero_stage <= 2:
|
| 218 |
-
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 219 |
-
exclude_frozen_parameters)
|
| 220 |
-
elif zero_stage == 3:
|
| 221 |
-
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 222 |
-
exclude_frozen_parameters)
|
| 223 |
-
|
| 224 |
-
|
| 225 |
-
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 226 |
-
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 227 |
-
return
|
| 228 |
-
|
| 229 |
-
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 230 |
-
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 231 |
-
|
| 232 |
-
if debug:
|
| 233 |
-
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 234 |
-
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 235 |
-
|
| 236 |
-
wanted_params = len(frozen_param_shapes)
|
| 237 |
-
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 238 |
-
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 239 |
-
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 240 |
-
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 241 |
-
|
| 242 |
-
total_params = 0
|
| 243 |
-
total_numel = 0
|
| 244 |
-
for name, shape in frozen_param_shapes.items():
|
| 245 |
-
total_params += 1
|
| 246 |
-
unpartitioned_numel = shape.numel()
|
| 247 |
-
total_numel += unpartitioned_numel
|
| 248 |
-
|
| 249 |
-
state_dict[name] = frozen_param_fragments[name]
|
| 250 |
-
|
| 251 |
-
if debug:
|
| 252 |
-
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 253 |
-
|
| 254 |
-
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 255 |
-
|
| 256 |
-
|
| 257 |
-
def _has_callable(obj, fn):
|
| 258 |
-
attr = getattr(obj, fn, None)
|
| 259 |
-
return callable(attr)
|
| 260 |
-
|
| 261 |
-
|
| 262 |
-
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 263 |
-
param_shapes = zero_model_states[0].param_shapes
|
| 264 |
-
|
| 265 |
-
# Reconstruction protocol:
|
| 266 |
-
#
|
| 267 |
-
# XXX: document this
|
| 268 |
-
|
| 269 |
-
if debug:
|
| 270 |
-
for i in range(world_size):
|
| 271 |
-
for j in range(len(fp32_flat_groups[0])):
|
| 272 |
-
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 273 |
-
|
| 274 |
-
# XXX: memory usage doubles here (zero2)
|
| 275 |
-
num_param_groups = len(fp32_flat_groups[0])
|
| 276 |
-
merged_single_partition_of_fp32_groups = []
|
| 277 |
-
for i in range(num_param_groups):
|
| 278 |
-
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 279 |
-
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 280 |
-
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 281 |
-
avail_numel = sum(
|
| 282 |
-
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 283 |
-
|
| 284 |
-
if debug:
|
| 285 |
-
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 286 |
-
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 287 |
-
# not asserting if there is a mismatch due to possible padding
|
| 288 |
-
print(f"Have {avail_numel} numels to process.")
|
| 289 |
-
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 290 |
-
|
| 291 |
-
# params
|
| 292 |
-
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 293 |
-
# out-of-core computing solution
|
| 294 |
-
total_numel = 0
|
| 295 |
-
total_params = 0
|
| 296 |
-
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 297 |
-
offset = 0
|
| 298 |
-
avail_numel = full_single_fp32_vector.numel()
|
| 299 |
-
for name, shape in shapes.items():
|
| 300 |
-
|
| 301 |
-
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
| 302 |
-
total_numel += unpartitioned_numel
|
| 303 |
-
total_params += 1
|
| 304 |
-
|
| 305 |
-
if debug:
|
| 306 |
-
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 307 |
-
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 308 |
-
offset += unpartitioned_numel
|
| 309 |
-
|
| 310 |
-
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 311 |
-
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 312 |
-
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 313 |
-
# live optimizer object, so we are checking that the numbers are within the right range
|
| 314 |
-
align_to = 2 * world_size
|
| 315 |
-
|
| 316 |
-
def zero2_align(x):
|
| 317 |
-
return align_to * math.ceil(x / align_to)
|
| 318 |
-
|
| 319 |
-
if debug:
|
| 320 |
-
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 321 |
-
|
| 322 |
-
offset = zero2_align(offset)
|
| 323 |
-
avail_numel = zero2_align(avail_numel)
|
| 324 |
-
|
| 325 |
-
if debug:
|
| 326 |
-
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 327 |
-
|
| 328 |
-
# Sanity check
|
| 329 |
-
if offset != avail_numel:
|
| 330 |
-
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 331 |
-
|
| 332 |
-
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 333 |
-
|
| 334 |
-
|
| 335 |
-
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 336 |
-
exclude_frozen_parameters):
|
| 337 |
-
state_dict = OrderedDict()
|
| 338 |
-
|
| 339 |
-
# buffers
|
| 340 |
-
buffers = zero_model_states[0].buffers
|
| 341 |
-
state_dict.update(buffers)
|
| 342 |
-
if debug:
|
| 343 |
-
print(f"added {len(buffers)} buffers")
|
| 344 |
-
|
| 345 |
-
if not exclude_frozen_parameters:
|
| 346 |
-
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 347 |
-
|
| 348 |
-
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 349 |
-
|
| 350 |
-
# recover shared parameters
|
| 351 |
-
for pair in zero_model_states[0].shared_params:
|
| 352 |
-
if pair[1] in state_dict:
|
| 353 |
-
state_dict[pair[0]] = state_dict[pair[1]]
|
| 354 |
-
|
| 355 |
-
return state_dict
|
| 356 |
-
|
| 357 |
-
|
| 358 |
-
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 359 |
-
remainder = unpartitioned_numel % world_size
|
| 360 |
-
padding_numel = (world_size - remainder) if remainder else 0
|
| 361 |
-
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 362 |
-
return partitioned_numel, padding_numel
|
| 363 |
-
|
| 364 |
-
|
| 365 |
-
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 366 |
-
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 367 |
-
return
|
| 368 |
-
|
| 369 |
-
if debug:
|
| 370 |
-
for i in range(world_size):
|
| 371 |
-
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 372 |
-
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 373 |
-
|
| 374 |
-
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 375 |
-
wanted_params = len(frozen_param_shapes)
|
| 376 |
-
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 377 |
-
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 378 |
-
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 379 |
-
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 380 |
-
|
| 381 |
-
total_params = 0
|
| 382 |
-
total_numel = 0
|
| 383 |
-
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 384 |
-
total_params += 1
|
| 385 |
-
unpartitioned_numel = shape.numel()
|
| 386 |
-
total_numel += unpartitioned_numel
|
| 387 |
-
|
| 388 |
-
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 389 |
-
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 390 |
-
|
| 391 |
-
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 392 |
-
|
| 393 |
-
if debug:
|
| 394 |
-
print(
|
| 395 |
-
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 396 |
-
)
|
| 397 |
-
|
| 398 |
-
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 399 |
-
|
| 400 |
-
|
| 401 |
-
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 402 |
-
param_shapes = zero_model_states[0].param_shapes
|
| 403 |
-
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 404 |
-
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 405 |
-
# param, re-consolidating each param, while dealing with padding if any
|
| 406 |
-
|
| 407 |
-
# merge list of dicts, preserving order
|
| 408 |
-
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 409 |
-
|
| 410 |
-
if debug:
|
| 411 |
-
for i in range(world_size):
|
| 412 |
-
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 413 |
-
|
| 414 |
-
wanted_params = len(param_shapes)
|
| 415 |
-
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 416 |
-
# not asserting if there is a mismatch due to possible padding
|
| 417 |
-
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 418 |
-
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 419 |
-
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 420 |
-
|
| 421 |
-
# params
|
| 422 |
-
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 423 |
-
# out-of-core computing solution
|
| 424 |
-
offset = 0
|
| 425 |
-
total_numel = 0
|
| 426 |
-
total_params = 0
|
| 427 |
-
for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
|
| 428 |
-
unpartitioned_numel = shape.numel()
|
| 429 |
-
total_numel += unpartitioned_numel
|
| 430 |
-
total_params += 1
|
| 431 |
-
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 432 |
-
|
| 433 |
-
if debug:
|
| 434 |
-
print(
|
| 435 |
-
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 436 |
-
)
|
| 437 |
-
|
| 438 |
-
# XXX: memory usage doubles here
|
| 439 |
-
state_dict[name] = torch.cat(
|
| 440 |
-
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
|
| 441 |
-
0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 442 |
-
offset += partitioned_numel
|
| 443 |
-
|
| 444 |
-
offset *= world_size
|
| 445 |
-
|
| 446 |
-
# Sanity check
|
| 447 |
-
if offset != avail_numel:
|
| 448 |
-
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 449 |
-
|
| 450 |
-
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 451 |
-
|
| 452 |
-
|
| 453 |
-
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 454 |
-
exclude_frozen_parameters):
|
| 455 |
-
state_dict = OrderedDict()
|
| 456 |
-
|
| 457 |
-
# buffers
|
| 458 |
-
buffers = zero_model_states[0].buffers
|
| 459 |
-
state_dict.update(buffers)
|
| 460 |
-
if debug:
|
| 461 |
-
print(f"added {len(buffers)} buffers")
|
| 462 |
-
|
| 463 |
-
if not exclude_frozen_parameters:
|
| 464 |
-
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 465 |
-
|
| 466 |
-
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 467 |
-
|
| 468 |
-
# recover shared parameters
|
| 469 |
-
for pair in zero_model_states[0].shared_params:
|
| 470 |
-
if pair[1] in state_dict:
|
| 471 |
-
state_dict[pair[0]] = state_dict[pair[1]]
|
| 472 |
-
|
| 473 |
-
return state_dict
|
| 474 |
-
|
| 475 |
-
|
| 476 |
-
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
|
| 477 |
-
"""
|
| 478 |
-
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 479 |
-
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 480 |
-
via a model hub.
|
| 481 |
-
|
| 482 |
-
Args:
|
| 483 |
-
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 484 |
-
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 485 |
-
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 486 |
-
|
| 487 |
-
Returns:
|
| 488 |
-
- pytorch ``state_dict``
|
| 489 |
-
|
| 490 |
-
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
|
| 491 |
-
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 492 |
-
the checkpoint.
|
| 493 |
-
|
| 494 |
-
A typical usage might be ::
|
| 495 |
-
|
| 496 |
-
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 497 |
-
# do the training and checkpoint saving
|
| 498 |
-
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 499 |
-
model = model.cpu() # move to cpu
|
| 500 |
-
model.load_state_dict(state_dict)
|
| 501 |
-
# submit to model hub or save the model to share with others
|
| 502 |
-
|
| 503 |
-
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 504 |
-
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 505 |
-
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 506 |
-
|
| 507 |
-
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 508 |
-
|
| 509 |
-
"""
|
| 510 |
-
if tag is None:
|
| 511 |
-
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 512 |
-
if os.path.isfile(latest_path):
|
| 513 |
-
with open(latest_path, 'r') as fd:
|
| 514 |
-
tag = fd.read().strip()
|
| 515 |
-
else:
|
| 516 |
-
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 517 |
-
|
| 518 |
-
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 519 |
-
|
| 520 |
-
if not os.path.isdir(ds_checkpoint_dir):
|
| 521 |
-
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 522 |
-
|
| 523 |
-
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
| 524 |
-
|
| 525 |
-
|
| 526 |
-
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
| 527 |
-
output_dir,
|
| 528 |
-
max_shard_size="5GB",
|
| 529 |
-
safe_serialization=False,
|
| 530 |
-
tag=None,
|
| 531 |
-
exclude_frozen_parameters=False):
|
| 532 |
-
"""
|
| 533 |
-
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 534 |
-
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 535 |
-
|
| 536 |
-
Args:
|
| 537 |
-
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 538 |
-
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
| 539 |
-
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
| 540 |
-
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
| 541 |
-
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 542 |
-
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 543 |
-
"""
|
| 544 |
-
# Dependency pre-check
|
| 545 |
-
if safe_serialization:
|
| 546 |
-
try:
|
| 547 |
-
from safetensors.torch import save_file
|
| 548 |
-
except ImportError:
|
| 549 |
-
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
| 550 |
-
raise
|
| 551 |
-
if max_shard_size is not None:
|
| 552 |
-
try:
|
| 553 |
-
from huggingface_hub import split_torch_state_dict_into_shards
|
| 554 |
-
except ImportError:
|
| 555 |
-
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
| 556 |
-
raise
|
| 557 |
-
|
| 558 |
-
# Convert zero checkpoint to state_dict
|
| 559 |
-
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
|
| 560 |
-
|
| 561 |
-
# Shard the model if it is too big.
|
| 562 |
-
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
| 563 |
-
if max_shard_size is not None:
|
| 564 |
-
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
| 565 |
-
state_dict_split = split_torch_state_dict_into_shards(state_dict,
|
| 566 |
-
filename_pattern=filename_pattern,
|
| 567 |
-
max_shard_size=max_shard_size)
|
| 568 |
-
else:
|
| 569 |
-
from collections import namedtuple
|
| 570 |
-
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
| 571 |
-
state_dict_split = StateDictSplit(is_sharded=False,
|
| 572 |
-
filename_to_tensors={weights_name: list(state_dict.keys())})
|
| 573 |
-
|
| 574 |
-
# Save the model
|
| 575 |
-
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
| 576 |
-
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
| 577 |
-
shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
|
| 578 |
-
output_path = os.path.join(output_dir, shard_file)
|
| 579 |
-
if safe_serialization:
|
| 580 |
-
save_file(shard, output_path, metadata={"format": "pt"})
|
| 581 |
-
else:
|
| 582 |
-
torch.save(shard, output_path)
|
| 583 |
-
|
| 584 |
-
# Save index if sharded
|
| 585 |
-
if state_dict_split.is_sharded:
|
| 586 |
-
index = {
|
| 587 |
-
"metadata": state_dict_split.metadata,
|
| 588 |
-
"weight_map": state_dict_split.tensor_to_filename,
|
| 589 |
-
}
|
| 590 |
-
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
| 591 |
-
save_index_file = os.path.join(output_dir, save_index_file)
|
| 592 |
-
with open(save_index_file, "w", encoding="utf-8") as f:
|
| 593 |
-
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
| 594 |
-
f.write(content)
|
| 595 |
-
|
| 596 |
-
|
| 597 |
-
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 598 |
-
"""
|
| 599 |
-
1. Put the provided model to cpu
|
| 600 |
-
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 601 |
-
3. Load it into the provided model
|
| 602 |
-
|
| 603 |
-
Args:
|
| 604 |
-
- ``model``: the model object to update
|
| 605 |
-
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 606 |
-
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 607 |
-
|
| 608 |
-
Returns:
|
| 609 |
-
- ``model`: modified model
|
| 610 |
-
|
| 611 |
-
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 612 |
-
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 613 |
-
conveniently placed for you in the checkpoint folder.
|
| 614 |
-
|
| 615 |
-
A typical usage might be ::
|
| 616 |
-
|
| 617 |
-
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 618 |
-
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 619 |
-
# submit to model hub or save the model to share with others
|
| 620 |
-
|
| 621 |
-
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 622 |
-
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 623 |
-
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 624 |
-
|
| 625 |
-
"""
|
| 626 |
-
logger.info(f"Extracting fp32 weights")
|
| 627 |
-
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 628 |
-
|
| 629 |
-
logger.info(f"Overwriting model with fp32 weights")
|
| 630 |
-
model = model.cpu()
|
| 631 |
-
model.load_state_dict(state_dict, strict=False)
|
| 632 |
-
|
| 633 |
-
return model
|
| 634 |
-
|
| 635 |
-
|
| 636 |
-
if __name__ == "__main__":
|
| 637 |
-
parser = argparse.ArgumentParser()
|
| 638 |
-
parser.add_argument("checkpoint_dir",
|
| 639 |
-
type=str,
|
| 640 |
-
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 641 |
-
parser.add_argument("output_dir",
|
| 642 |
-
type=str,
|
| 643 |
-
help="directory to the pytorch fp32 state_dict output files"
|
| 644 |
-
"(e.g. path/checkpoint-12-output/)")
|
| 645 |
-
parser.add_argument(
|
| 646 |
-
"--max_shard_size",
|
| 647 |
-
type=str,
|
| 648 |
-
default="5GB",
|
| 649 |
-
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
| 650 |
-
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
| 651 |
-
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
| 652 |
-
"without CPU OOM issues.")
|
| 653 |
-
parser.add_argument(
|
| 654 |
-
"--safe_serialization",
|
| 655 |
-
default=False,
|
| 656 |
-
action='store_true',
|
| 657 |
-
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
| 658 |
-
parser.add_argument("-t",
|
| 659 |
-
"--tag",
|
| 660 |
-
type=str,
|
| 661 |
-
default=None,
|
| 662 |
-
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
| 663 |
-
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
| 664 |
-
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 665 |
-
args = parser.parse_args()
|
| 666 |
-
|
| 667 |
-
debug = args.debug
|
| 668 |
-
|
| 669 |
-
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
| 670 |
-
args.output_dir,
|
| 671 |
-
max_shard_size=args.max_shard_size,
|
| 672 |
-
safe_serialization=args.safe_serialization,
|
| 673 |
-
tag=args.tag,
|
| 674 |
-
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|