Upload folder using huggingface_hub

checkpoints/checkpoint-900/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "/root/open-r1/checkpoints/meta-llama/Llama-3.2-1B-Instruct/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

checkpoints/checkpoint-900/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.49.0.dev0"
+}

checkpoints/checkpoint-900/global_step900/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d6bf6cee495523ac6fc19c1ae85cc66c0402e494e79e8273ee9223bacd1f0c2
+size 3707447984

checkpoints/checkpoint-900/global_step900/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ff302b03e315bc3dadefc12b331b9d8f441c2d434dcd7ace6988b3a4899bbf
+size 3707447984

checkpoints/checkpoint-900/global_step900/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e89cb27bfc2b714613219126b07eee6a1dd5339104061549056618ffcfbc31d3
+size 3707447984

checkpoints/checkpoint-900/global_step900/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65b65a4e29c8aefc1a051b7ce234d0897d40280fc01c4e2bbcc91e86037881dc
+size 3707447984

checkpoints/checkpoint-900/global_step900/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4f0586d4eeef8444a5875b013789df4929aca9fc3d6e79715825bb5eff91ab2
+size 75384

checkpoints/checkpoint-900/global_step900/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:602896dfa0ba233ca45d33ebba6047a7b959d7bed67329f29ca4b1395486af8d
+size 75320

checkpoints/checkpoint-900/global_step900/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4e64bfaae681ce6019b60875fd5f3513a6ce2d5d3beb8c4dad8ff3c68f3905d
+size 75320

checkpoints/checkpoint-900/global_step900/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9dcb5835d47b7453eb34258d7b6589f5b17eb159d2e2d3a96193cd34077e161
+size 75320

checkpoints/checkpoint-900/latest

@@ -0,0 +1 @@
+global_step900

checkpoints/checkpoint-900/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:084a75537bb0b59dce7c866406a247d7976305d52645a56edc44b8e8f755c30f
+size 2471645608

checkpoints/checkpoint-900/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae78313eb528c8d3695eebaf4de3539bd0a0bc6ee18c66af1ee183442f1758a0
+size 15024

checkpoints/checkpoint-900/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b38031f60d9e88601d369ef46bcdcf2b5b03f2cb4ba93853bcb2328df7ebb7c
+size 15024

checkpoints/checkpoint-900/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58092375c93d237cd0e3149aecfbf83e2acdae46279e07a32920d01cb507e64
+size 15024

checkpoints/checkpoint-900/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83cd4bbff9962da7ec6787fcea8d65df7096917f9a5902e249ba7aee8887fe5f
+size 15024

checkpoints/checkpoint-900/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03746929464b54010bdb23b85c112256bc4e1d2793521314f052727b3ea9e68f
+size 1064

checkpoints/checkpoint-900/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

checkpoints/checkpoint-900/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

checkpoints/checkpoint-900/tokenizer_config.json

@@ -0,0 +1,2064 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "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",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoints/checkpoint-900/trainer_state.json

@@ -0,0 +1,1365 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.759571209800919,
+  "eval_steps": 100,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015313935681470138,
+      "grad_norm": 3.8326407564846536,
+      "learning_rate": 6.134969325153375e-07,
+      "loss": 1.3339,
+      "step": 5
+    },
+    {
+      "epoch": 0.030627871362940276,
+      "grad_norm": 3.5496788557416803,
+      "learning_rate": 1.226993865030675e-06,
+      "loss": 1.3517,
+      "step": 10
+    },
+    {
+      "epoch": 0.045941807044410414,
+      "grad_norm": 2.292172802820395,
+      "learning_rate": 1.8404907975460124e-06,
+      "loss": 1.3142,
+      "step": 15
+    },
+    {
+      "epoch": 0.06125574272588055,
+      "grad_norm": 1.7775340318261912,
+      "learning_rate": 2.45398773006135e-06,
+      "loss": 1.2477,
+      "step": 20
+    },
+    {
+      "epoch": 0.07656967840735068,
+      "grad_norm": 1.4368794370978828,
+      "learning_rate": 3.0674846625766875e-06,
+      "loss": 1.2037,
+      "step": 25
+    },
+    {
+      "epoch": 0.09188361408882083,
+      "grad_norm": 1.061354555879628,
+      "learning_rate": 3.680981595092025e-06,
+      "loss": 1.1505,
+      "step": 30
+    },
+    {
+      "epoch": 0.10719754977029096,
+      "grad_norm": 0.8377616484610274,
+      "learning_rate": 4.294478527607362e-06,
+      "loss": 1.1179,
+      "step": 35
+    },
+    {
+      "epoch": 0.1225114854517611,
+      "grad_norm": 0.7884987790196414,
+      "learning_rate": 4.9079754601227e-06,
+      "loss": 1.0735,
+      "step": 40
+    },
+    {
+      "epoch": 0.13782542113323124,
+      "grad_norm": 0.7279957151761491,
+      "learning_rate": 5.521472392638038e-06,
+      "loss": 1.0556,
+      "step": 45
+    },
+    {
+      "epoch": 0.15313935681470137,
+      "grad_norm": 0.6692858930956382,
+      "learning_rate": 6.134969325153375e-06,
+      "loss": 1.0294,
+      "step": 50
+    },
+    {
+      "epoch": 0.16845329249617153,
+      "grad_norm": 0.6401840707040195,
+      "learning_rate": 6.748466257668712e-06,
+      "loss": 1.0175,
+      "step": 55
+    },
+    {
+      "epoch": 0.18376722817764166,
+      "grad_norm": 0.6584204446837412,
+      "learning_rate": 7.36196319018405e-06,
+      "loss": 1.0283,
+      "step": 60
+    },
+    {
+      "epoch": 0.1990811638591118,
+      "grad_norm": 0.6647811794468166,
+      "learning_rate": 7.975460122699386e-06,
+      "loss": 0.9799,
+      "step": 65
+    },
+    {
+      "epoch": 0.21439509954058192,
+      "grad_norm": 0.6774675226534475,
+      "learning_rate": 8.588957055214725e-06,
+      "loss": 0.969,
+      "step": 70
+    },
+    {
+      "epoch": 0.22970903522205208,
+      "grad_norm": 0.6918496726012217,
+      "learning_rate": 9.202453987730062e-06,
+      "loss": 0.9787,
+      "step": 75
+    },
+    {
+      "epoch": 0.2450229709035222,
+      "grad_norm": 0.6740082248654927,
+      "learning_rate": 9.8159509202454e-06,
+      "loss": 0.9596,
+      "step": 80
+    },
+    {
+      "epoch": 0.26033690658499237,
+      "grad_norm": 0.6791518891702232,
+      "learning_rate": 1.0429447852760737e-05,
+      "loss": 0.9813,
+      "step": 85
+    },
+    {
+      "epoch": 0.27565084226646247,
+      "grad_norm": 0.7029695620068616,
+      "learning_rate": 1.1042944785276076e-05,
+      "loss": 0.9703,
+      "step": 90
+    },
+    {
+      "epoch": 0.29096477794793263,
+      "grad_norm": 0.6355433423695775,
+      "learning_rate": 1.1656441717791411e-05,
+      "loss": 0.9375,
+      "step": 95
+    },
+    {
+      "epoch": 0.30627871362940273,
+      "grad_norm": 0.6551855479751819,
+      "learning_rate": 1.226993865030675e-05,
+      "loss": 0.952,
+      "step": 100
+    },
+    {
+      "epoch": 0.30627871362940273,
+      "eval_loss": 0.964697003364563,
+      "eval_runtime": 3.4019,
+      "eval_samples_per_second": 36.45,
+      "eval_steps_per_second": 2.352,
+      "step": 100
+    },
+    {
+      "epoch": 0.3215926493108729,
+      "grad_norm": 0.6655305965463972,
+      "learning_rate": 1.2883435582822085e-05,
+      "loss": 0.9237,
+      "step": 105
+    },
+    {
+      "epoch": 0.33690658499234305,
+      "grad_norm": 0.7257201177401903,
+      "learning_rate": 1.3496932515337424e-05,
+      "loss": 0.9511,
+      "step": 110
+    },
+    {
+      "epoch": 0.35222052067381315,
+      "grad_norm": 0.7424667090609683,
+      "learning_rate": 1.4110429447852763e-05,
+      "loss": 0.9323,
+      "step": 115
+    },
+    {
+      "epoch": 0.3675344563552833,
+      "grad_norm": 0.7336582339806711,
+      "learning_rate": 1.47239263803681e-05,
+      "loss": 0.9449,
+      "step": 120
+    },
+    {
+      "epoch": 0.38284839203675347,
+      "grad_norm": 0.6851538651091853,
+      "learning_rate": 1.5337423312883436e-05,
+      "loss": 0.9133,
+      "step": 125
+    },
+    {
+      "epoch": 0.3981623277182236,
+      "grad_norm": 0.7424313941044212,
+      "learning_rate": 1.5950920245398772e-05,
+      "loss": 0.9173,
+      "step": 130
+    },
+    {
+      "epoch": 0.41347626339969373,
+      "grad_norm": 0.7937170928985942,
+      "learning_rate": 1.656441717791411e-05,
+      "loss": 0.9348,
+      "step": 135
+    },
+    {
+      "epoch": 0.42879019908116384,
+      "grad_norm": 0.7668730085289572,
+      "learning_rate": 1.717791411042945e-05,
+      "loss": 0.9091,
+      "step": 140
+    },
+    {
+      "epoch": 0.444104134762634,
+      "grad_norm": 0.713212902268727,
+      "learning_rate": 1.7791411042944788e-05,
+      "loss": 0.9054,
+      "step": 145
+    },
+    {
+      "epoch": 0.45941807044410415,
+      "grad_norm": 0.8266274957992115,
+      "learning_rate": 1.8404907975460123e-05,
+      "loss": 0.9165,
+      "step": 150
+    },
+    {
+      "epoch": 0.47473200612557426,
+      "grad_norm": 0.7773849012810377,
+      "learning_rate": 1.9018404907975462e-05,
+      "loss": 0.9261,
+      "step": 155
+    },
+    {
+      "epoch": 0.4900459418070444,
+      "grad_norm": 0.7698543962501324,
+      "learning_rate": 1.96319018404908e-05,
+      "loss": 0.8848,
+      "step": 160
+    },
+    {
+      "epoch": 0.5053598774885145,
+      "grad_norm": 0.7326492641075325,
+      "learning_rate": 1.9999908278985548e-05,
+      "loss": 0.9002,
+      "step": 165
+    },
+    {
+      "epoch": 0.5206738131699847,
+      "grad_norm": 0.725915155149828,
+      "learning_rate": 1.9998876436895888e-05,
+      "loss": 0.9064,
+      "step": 170
+    },
+    {
+      "epoch": 0.5359877488514548,
+      "grad_norm": 0.7137681931522117,
+      "learning_rate": 1.99966982201439e-05,
+      "loss": 0.9083,
+      "step": 175
+    },
+    {
+      "epoch": 0.5513016845329249,
+      "grad_norm": 0.8244990854189328,
+      "learning_rate": 1.9993373878462894e-05,
+      "loss": 0.8988,
+      "step": 180
+    },
+    {
+      "epoch": 0.5666156202143952,
+      "grad_norm": 0.7883005110592801,
+      "learning_rate": 1.99889037929898e-05,
+      "loss": 0.9021,
+      "step": 185
+    },
+    {
+      "epoch": 0.5819295558958653,
+      "grad_norm": 0.7224060026030372,
+      "learning_rate": 1.9983288476221482e-05,
+      "loss": 0.8881,
+      "step": 190
+    },
+    {
+      "epoch": 0.5972434915773354,
+      "grad_norm": 0.7010662098507998,
+      "learning_rate": 1.9976528571955946e-05,
+      "loss": 0.8889,
+      "step": 195
+    },
+    {
+      "epoch": 0.6125574272588055,
+      "grad_norm": 0.7154815490781321,
+      "learning_rate": 1.9968624855218578e-05,
+      "loss": 0.8884,
+      "step": 200
+    },
+    {
+      "epoch": 0.6125574272588055,
+      "eval_loss": 0.9119902849197388,
+      "eval_runtime": 3.4604,
+      "eval_samples_per_second": 35.834,
+      "eval_steps_per_second": 2.312,
+      "step": 200
+    },
+    {
+      "epoch": 0.6278713629402757,
+      "grad_norm": 0.6984184509316927,
+      "learning_rate": 1.995957823217325e-05,
+      "loss": 0.9033,
+      "step": 205
+    },
+    {
+      "epoch": 0.6431852986217458,
+      "grad_norm": 0.7120998555383481,
+      "learning_rate": 1.9949389740018438e-05,
+      "loss": 0.8988,
+      "step": 210
+    },
+    {
+      "epoch": 0.6584992343032159,
+      "grad_norm": 0.66696186884436,
+      "learning_rate": 1.993806054686832e-05,
+      "loss": 0.8735,
+      "step": 215
+    },
+    {
+      "epoch": 0.6738131699846861,
+      "grad_norm": 0.7395425655626215,
+      "learning_rate": 1.9925591951618822e-05,
+      "loss": 0.9127,
+      "step": 220
+    },
+    {
+      "epoch": 0.6891271056661562,
+      "grad_norm": 0.6960401538019414,
+      "learning_rate": 1.9911985383798737e-05,
+      "loss": 0.875,
+      "step": 225
+    },
+    {
+      "epoch": 0.7044410413476263,
+      "grad_norm": 0.7195874036136765,
+      "learning_rate": 1.9897242403405792e-05,
+      "loss": 0.8782,
+      "step": 230
+    },
+    {
+      "epoch": 0.7197549770290965,
+      "grad_norm": 0.7129931764921758,
+      "learning_rate": 1.9881364700727827e-05,
+      "loss": 0.8943,
+      "step": 235
+    },
+    {
+      "epoch": 0.7350689127105666,
+      "grad_norm": 0.690645634714852,
+      "learning_rate": 1.9864354096148966e-05,
+      "loss": 0.8782,
+      "step": 240
+    },
+    {
+      "epoch": 0.7503828483920367,
+      "grad_norm": 0.7055958514936376,
+      "learning_rate": 1.9846212539940955e-05,
+      "loss": 0.8867,
+      "step": 245
+    },
+    {
+      "epoch": 0.7656967840735069,
+      "grad_norm": 0.7517885221069497,
+      "learning_rate": 1.982694211203952e-05,
+      "loss": 0.8843,
+      "step": 250
+    },
+    {
+      "epoch": 0.781010719754977,
+      "grad_norm": 0.7270711746255435,
+      "learning_rate": 1.9806545021805922e-05,
+      "loss": 0.8757,
+      "step": 255
+    },
+    {
+      "epoch": 0.7963246554364471,
+      "grad_norm": 0.707252502344583,
+      "learning_rate": 1.9785023607773655e-05,
+      "loss": 0.8842,
+      "step": 260
+    },
+    {
+      "epoch": 0.8116385911179173,
+      "grad_norm": 0.8083132789219781,
+      "learning_rate": 1.976238033738033e-05,
+      "loss": 0.8578,
+      "step": 265
+    },
+    {
+      "epoch": 0.8269525267993875,
+      "grad_norm": 0.7287731737231247,
+      "learning_rate": 1.9738617806684767e-05,
+      "loss": 0.911,
+      "step": 270
+    },
+    {
+      "epoch": 0.8422664624808576,
+      "grad_norm": 0.7683997901360534,
+      "learning_rate": 1.9713738740069384e-05,
+      "loss": 0.8607,
+      "step": 275
+    },
+    {
+      "epoch": 0.8575803981623277,
+      "grad_norm": 0.6883196631913017,
+      "learning_rate": 1.9687745989927823e-05,
+      "loss": 0.8781,
+      "step": 280
+    },
+    {
+      "epoch": 0.8728943338437979,
+      "grad_norm": 0.7137416791751114,
+      "learning_rate": 1.966064253633793e-05,
+      "loss": 0.8675,
+      "step": 285
+    },
+    {
+      "epoch": 0.888208269525268,
+      "grad_norm": 0.800711538711323,
+      "learning_rate": 1.963243148672009e-05,
+      "loss": 0.8696,
+      "step": 290
+    },
+    {
+      "epoch": 0.9035222052067381,
+      "grad_norm": 0.7017619169785259,
+      "learning_rate": 1.960311607548096e-05,
+      "loss": 0.8724,
+      "step": 295
+    },
+    {
+      "epoch": 0.9188361408882083,
+      "grad_norm": 0.7347091076360852,
+      "learning_rate": 1.957269966364263e-05,
+      "loss": 0.8753,
+      "step": 300
+    },
+    {
+      "epoch": 0.9188361408882083,
+      "eval_loss": 0.8846515417098999,
+      "eval_runtime": 3.4431,
+      "eval_samples_per_second": 36.014,
+      "eval_steps_per_second": 2.323,
+      "step": 300
+    },
+    {
+      "epoch": 0.9341500765696784,
+      "grad_norm": 0.6840257399223311,
+      "learning_rate": 1.9541185738457304e-05,
+      "loss": 0.8661,
+      "step": 305
+    },
+    {
+      "epoch": 0.9494640122511485,
+      "grad_norm": 0.6350789314835292,
+      "learning_rate": 1.9508577913007475e-05,
+      "loss": 0.866,
+      "step": 310
+    },
+    {
+      "epoch": 0.9647779479326187,
+      "grad_norm": 0.742666392443459,
+      "learning_rate": 1.9474879925791665e-05,
+      "loss": 0.8712,
+      "step": 315
+    },
+    {
+      "epoch": 0.9800918836140888,
+      "grad_norm": 0.7707700113231902,
+      "learning_rate": 1.944009564029584e-05,
+      "loss": 0.8656,
+      "step": 320
+    },
+    {
+      "epoch": 0.9954058192955589,
+      "grad_norm": 0.7026681496550549,
+      "learning_rate": 1.9404229044550432e-05,
+      "loss": 0.8707,
+      "step": 325
+    },
+    {
+      "epoch": 1.0122511485451762,
+      "grad_norm": 0.8698658929763603,
+      "learning_rate": 1.9367284250673126e-05,
+      "loss": 1.0103,
+      "step": 330
+    },
+    {
+      "epoch": 1.0275650842266462,
+      "grad_norm": 0.7696705674515646,
+      "learning_rate": 1.9329265494397386e-05,
+      "loss": 0.8254,
+      "step": 335
+    },
+    {
+      "epoch": 1.0428790199081164,
+      "grad_norm": 0.703085270940529,
+      "learning_rate": 1.929017713458685e-05,
+      "loss": 0.7994,
+      "step": 340
+    },
+    {
+      "epoch": 1.0581929555895866,
+      "grad_norm": 0.7281489106195598,
+      "learning_rate": 1.9250023652735573e-05,
+      "loss": 0.7997,
+      "step": 345
+    },
+    {
+      "epoch": 1.0735068912710566,
+      "grad_norm": 0.6721859356177987,
+      "learning_rate": 1.920880965245422e-05,
+      "loss": 0.8028,
+      "step": 350
+    },
+    {
+      "epoch": 1.0888208269525268,
+      "grad_norm": 0.6999456629939552,
+      "learning_rate": 1.9166539858942258e-05,
+      "loss": 0.7923,
+      "step": 355
+    },
+    {
+      "epoch": 1.104134762633997,
+      "grad_norm": 0.761057382772568,
+      "learning_rate": 1.912321911844622e-05,
+      "loss": 0.8023,
+      "step": 360
+    },
+    {
+      "epoch": 1.119448698315467,
+      "grad_norm": 0.7613985157569584,
+      "learning_rate": 1.907885239770408e-05,
+      "loss": 0.8171,
+      "step": 365
+    },
+    {
+      "epoch": 1.1347626339969372,
+      "grad_norm": 0.7130602486133167,
+      "learning_rate": 1.9033444783375806e-05,
+      "loss": 0.8136,
+      "step": 370
+    },
+    {
+      "epoch": 1.1500765696784074,
+      "grad_norm": 0.7290477717213912,
+      "learning_rate": 1.8987001481460177e-05,
+      "loss": 0.7956,
+      "step": 375
+    },
+    {
+      "epoch": 1.1653905053598774,
+      "grad_norm": 0.6942113670274667,
+      "learning_rate": 1.8939527816697917e-05,
+      "loss": 0.795,
+      "step": 380
+    },
+    {
+      "epoch": 1.1807044410413476,
+      "grad_norm": 0.7278550945084655,
+      "learning_rate": 1.8891029231961208e-05,
+      "loss": 0.8038,
+      "step": 385
+    },
+    {
+      "epoch": 1.1960183767228179,
+      "grad_norm": 0.7637922924754829,
+      "learning_rate": 1.8841511287629667e-05,
+      "loss": 0.7941,
+      "step": 390
+    },
+    {
+      "epoch": 1.2113323124042878,
+      "grad_norm": 0.7227667767094055,
+      "learning_rate": 1.8790979660952832e-05,
+      "loss": 0.7899,
+      "step": 395
+    },
+    {
+      "epoch": 1.226646248085758,
+      "grad_norm": 0.6856723635729023,
+      "learning_rate": 1.8739440145399295e-05,
+      "loss": 0.8037,
+      "step": 400
+    },
+    {
+      "epoch": 1.226646248085758,
+      "eval_loss": 0.8724085092544556,
+      "eval_runtime": 3.6883,
+      "eval_samples_per_second": 33.619,
+      "eval_steps_per_second": 2.169,
+      "step": 400
+    },
+    {
+      "epoch": 1.2419601837672283,
+      "grad_norm": 0.6585093868236329,
+      "learning_rate": 1.8686898649992437e-05,
+      "loss": 0.7969,
+      "step": 405
+    },
+    {
+      "epoch": 1.2572741194486983,
+      "grad_norm": 0.6787675213944868,
+      "learning_rate": 1.8633361198632987e-05,
+      "loss": 0.8077,
+      "step": 410
+    },
+    {
+      "epoch": 1.2725880551301685,
+      "grad_norm": 0.6808724401749536,
+      "learning_rate": 1.857883392940837e-05,
+      "loss": 0.8077,
+      "step": 415
+    },
+    {
+      "epoch": 1.2879019908116387,
+      "grad_norm": 0.6824672080638723,
+      "learning_rate": 1.8523323093888983e-05,
+      "loss": 0.8025,
+      "step": 420
+    },
+    {
+      "epoch": 1.3032159264931087,
+      "grad_norm": 0.6611632916751219,
+      "learning_rate": 1.8466835056411422e-05,
+      "loss": 0.7875,
+      "step": 425
+    },
+    {
+      "epoch": 1.318529862174579,
+      "grad_norm": 0.701746007873801,
+      "learning_rate": 1.8409376293348836e-05,
+      "loss": 0.794,
+      "step": 430
+    },
+    {
+      "epoch": 1.3338437978560491,
+      "grad_norm": 0.6668057827943388,
+      "learning_rate": 1.8350953392368408e-05,
+      "loss": 0.797,
+      "step": 435
+    },
+    {
+      "epoch": 1.349157733537519,
+      "grad_norm": 0.7077024335619939,
+      "learning_rate": 1.8291573051676063e-05,
+      "loss": 0.8257,
+      "step": 440
+    },
+    {
+      "epoch": 1.3644716692189893,
+      "grad_norm": 0.7168213984013295,
+      "learning_rate": 1.8231242079248512e-05,
+      "loss": 0.7934,
+      "step": 445
+    },
+    {
+      "epoch": 1.3797856049004595,
+      "grad_norm": 0.7308258264034365,
+      "learning_rate": 1.816996739205274e-05,
+      "loss": 0.8078,
+      "step": 450
+    },
+    {
+      "epoch": 1.3950995405819295,
+      "grad_norm": 0.7935757091141241,
+      "learning_rate": 1.810775601525296e-05,
+      "loss": 0.8172,
+      "step": 455
+    },
+    {
+      "epoch": 1.4104134762633997,
+      "grad_norm": 0.7960723044086886,
+      "learning_rate": 1.8044615081405153e-05,
+      "loss": 0.7973,
+      "step": 460
+    },
+    {
+      "epoch": 1.42572741194487,
+      "grad_norm": 0.7013219126306894,
+      "learning_rate": 1.7980551829639357e-05,
+      "loss": 0.7928,
+      "step": 465
+    },
+    {
+      "epoch": 1.44104134762634,
+      "grad_norm": 0.7030096980783208,
+      "learning_rate": 1.7915573604829684e-05,
+      "loss": 0.7891,
+      "step": 470
+    },
+    {
+      "epoch": 1.4563552833078102,
+      "grad_norm": 0.7129952798275541,
+      "learning_rate": 1.784968785675221e-05,
+      "loss": 0.7964,
+      "step": 475
+    },
+    {
+      "epoch": 1.4716692189892804,
+      "grad_norm": 0.7042351661303197,
+      "learning_rate": 1.7782902139230876e-05,
+      "loss": 0.7821,
+      "step": 480
+    },
+    {
+      "epoch": 1.4869831546707504,
+      "grad_norm": 0.7412846210916867,
+      "learning_rate": 1.7715224109271426e-05,
+      "loss": 0.7983,
+      "step": 485
+    },
+    {
+      "epoch": 1.5022970903522204,
+      "grad_norm": 0.7586380261564012,
+      "learning_rate": 1.764666152618355e-05,
+      "loss": 0.8167,
+      "step": 490
+    },
+    {
+      "epoch": 1.5176110260336908,
+      "grad_norm": 0.784243612804958,
+      "learning_rate": 1.7577222250691254e-05,
+      "loss": 0.8086,
+      "step": 495
+    },
+    {
+      "epoch": 1.5329249617151608,
+      "grad_norm": 0.6901397300587065,
+      "learning_rate": 1.7506914244031627e-05,
+      "loss": 0.7966,
+      "step": 500
+    },
+    {
+      "epoch": 1.5329249617151608,
+      "eval_loss": 0.8608717918395996,
+      "eval_runtime": 4.0604,
+      "eval_samples_per_second": 30.539,
+      "eval_steps_per_second": 1.97,
+      "step": 500
+    },
+    {
+      "epoch": 1.5482388973966308,
+      "grad_norm": 0.6826627810241662,
+      "learning_rate": 1.7435745567042096e-05,
+      "loss": 0.7871,
+      "step": 505
+    },
+    {
+      "epoch": 1.5635528330781012,
+      "grad_norm": 0.7329202799692207,
+      "learning_rate": 1.7363724379236237e-05,
+      "loss": 0.806,
+      "step": 510
+    },
+    {
+      "epoch": 1.5788667687595712,
+      "grad_norm": 0.8605855369920612,
+      "learning_rate": 1.7290858937868296e-05,
+      "loss": 0.8134,
+      "step": 515
+    },
+    {
+      "epoch": 1.5941807044410412,
+      "grad_norm": 0.6963610579257828,
+      "learning_rate": 1.7217157596986474e-05,
+      "loss": 0.8057,
+      "step": 520
+    },
+    {
+      "epoch": 1.6094946401225116,
+      "grad_norm": 0.715201778907277,
+      "learning_rate": 1.7142628806475144e-05,
+      "loss": 0.806,
+      "step": 525
+    },
+    {
+      "epoch": 1.6248085758039816,
+      "grad_norm": 0.7191782284781755,
+      "learning_rate": 1.706728111108607e-05,
+      "loss": 0.8027,
+      "step": 530
+    },
+    {
+      "epoch": 1.6401225114854516,
+      "grad_norm": 0.6872215034145709,
+      "learning_rate": 1.699112314945874e-05,
+      "loss": 0.7953,
+      "step": 535
+    },
+    {
+      "epoch": 1.655436447166922,
+      "grad_norm": 0.7008995671254957,
+      "learning_rate": 1.691416365312996e-05,
+      "loss": 0.8096,
+      "step": 540
+    },
+    {
+      "epoch": 1.670750382848392,
+      "grad_norm": 0.6521306963395784,
+      "learning_rate": 1.683641144553275e-05,
+      "loss": 0.7921,
+      "step": 545
+    },
+    {
+      "epoch": 1.686064318529862,
+      "grad_norm": 0.6632532080286483,
+      "learning_rate": 1.675787544098477e-05,
+      "loss": 0.8056,
+      "step": 550
+    },
+    {
+      "epoch": 1.7013782542113323,
+      "grad_norm": 0.6547969582532698,
+      "learning_rate": 1.667856464366626e-05,
+      "loss": 0.7819,
+      "step": 555
+    },
+    {
+      "epoch": 1.7166921898928025,
+      "grad_norm": 0.7046901763937415,
+      "learning_rate": 1.6598488146587733e-05,
+      "loss": 0.8061,
+      "step": 560
+    },
+    {
+      "epoch": 1.7320061255742725,
+      "grad_norm": 0.6788820639858653,
+      "learning_rate": 1.6517655130547435e-05,
+      "loss": 0.7997,
+      "step": 565
+    },
+    {
+      "epoch": 1.7473200612557427,
+      "grad_norm": 0.6894021837769623,
+      "learning_rate": 1.6436074863078783e-05,
+      "loss": 0.803,
+      "step": 570
+    },
+    {
+      "epoch": 1.762633996937213,
+      "grad_norm": 0.7360294460315284,
+      "learning_rate": 1.635375669738782e-05,
+      "loss": 0.7975,
+      "step": 575
+    },
+    {
+      "epoch": 1.777947932618683,
+      "grad_norm": 0.6850098881910617,
+      "learning_rate": 1.627071007128089e-05,
+      "loss": 0.7825,
+      "step": 580
+    },
+    {
+      "epoch": 1.793261868300153,
+      "grad_norm": 0.7278655150611072,
+      "learning_rate": 1.618694450608256e-05,
+      "loss": 0.7955,
+      "step": 585
+    },
+    {
+      "epoch": 1.8085758039816233,
+      "grad_norm": 0.7122173514963583,
+      "learning_rate": 1.6102469605544036e-05,
+      "loss": 0.808,
+      "step": 590
+    },
+    {
+      "epoch": 1.8238897396630933,
+      "grad_norm": 0.6925118679066572,
+      "learning_rate": 1.6017295054742045e-05,
+      "loss": 0.7875,
+      "step": 595
+    },
+    {
+      "epoch": 1.8392036753445635,
+      "grad_norm": 0.6857769438421079,
+      "learning_rate": 1.5931430618968476e-05,
+      "loss": 0.7884,
+      "step": 600
+    },
+    {
+      "epoch": 1.8392036753445635,
+      "eval_loss": 0.8516013622283936,
+      "eval_runtime": 4.2451,
+      "eval_samples_per_second": 29.21,
+      "eval_steps_per_second": 1.885,
+      "step": 600
+    },
+    {
+      "epoch": 1.8545176110260337,
+      "grad_norm": 0.6326947636704211,
+      "learning_rate": 1.5844886142610763e-05,
+      "loss": 0.7819,
+      "step": 605
+    },
+    {
+      "epoch": 1.8698315467075037,
+      "grad_norm": 0.666694114425699,
+      "learning_rate": 1.575767154802323e-05,
+      "loss": 0.7777,
+      "step": 610
+    },
+    {
+      "epoch": 1.885145482388974,
+      "grad_norm": 0.6182711467351976,
+      "learning_rate": 1.5669796834389496e-05,
+      "loss": 0.7889,
+      "step": 615
+    },
+    {
+      "epoch": 1.9004594180704442,
+      "grad_norm": 0.6402744830423595,
+      "learning_rate": 1.5581272076576047e-05,
+      "loss": 0.7839,
+      "step": 620
+    },
+    {
+      "epoch": 1.9157733537519142,
+      "grad_norm": 0.6612456968952057,
+      "learning_rate": 1.5492107423977167e-05,
+      "loss": 0.7884,
+      "step": 625
+    },
+    {
+      "epoch": 1.9310872894333844,
+      "grad_norm": 0.6757984187665057,
+      "learning_rate": 1.5402313099351302e-05,
+      "loss": 0.7784,
+      "step": 630
+    },
+    {
+      "epoch": 1.9464012251148546,
+      "grad_norm": 0.6707442527908725,
+      "learning_rate": 1.5311899397649e-05,
+      "loss": 0.7935,
+      "step": 635
+    },
+    {
+      "epoch": 1.9617151607963246,
+      "grad_norm": 0.787792189502549,
+      "learning_rate": 1.522087668483264e-05,
+      "loss": 0.779,
+      "step": 640
+    },
+    {
+      "epoch": 1.9770290964777948,
+      "grad_norm": 0.6925473058613637,
+      "learning_rate": 1.5129255396687899e-05,
+      "loss": 0.7891,
+      "step": 645
+    },
+    {
+      "epoch": 1.992343032159265,
+      "grad_norm": 0.6890667970589922,
+      "learning_rate": 1.503704603762734e-05,
+      "loss": 0.7693,
+      "step": 650
+    },
+    {
+      "epoch": 2.009188361408882,
+      "grad_norm": 0.8106643045129424,
+      "learning_rate": 1.4944259179486068e-05,
+      "loss": 0.9039,
+      "step": 655
+    },
+    {
+      "epoch": 2.0245022970903523,
+      "grad_norm": 0.7728005094053498,
+      "learning_rate": 1.4850905460309648e-05,
+      "loss": 0.7116,
+      "step": 660
+    },
+    {
+      "epoch": 2.0398162327718223,
+      "grad_norm": 0.7301328106464207,
+      "learning_rate": 1.4756995583134463e-05,
+      "loss": 0.7313,
+      "step": 665
+    },
+    {
+      "epoch": 2.0551301684532923,
+      "grad_norm": 0.702048383564715,
+      "learning_rate": 1.4662540314760608e-05,
+      "loss": 0.7222,
+      "step": 670
+    },
+    {
+      "epoch": 2.0704441041347628,
+      "grad_norm": 0.7081084536553046,
+      "learning_rate": 1.4567550484517456e-05,
+      "loss": 0.7214,
+      "step": 675
+    },
+    {
+      "epoch": 2.0857580398162328,
+      "grad_norm": 0.7492389283409402,
+      "learning_rate": 1.4472036983022106e-05,
+      "loss": 0.7251,
+      "step": 680
+    },
+    {
+      "epoch": 2.1010719754977027,
+      "grad_norm": 0.7183839129962212,
+      "learning_rate": 1.437601076093073e-05,
+      "loss": 0.71,
+      "step": 685
+    },
+    {
+      "epoch": 2.116385911179173,
+      "grad_norm": 0.6904647110507196,
+      "learning_rate": 1.4279482827683095e-05,
+      "loss": 0.724,
+      "step": 690
+    },
+    {
+      "epoch": 2.131699846860643,
+      "grad_norm": 0.6745352346306862,
+      "learning_rate": 1.4182464250240341e-05,
+      "loss": 0.7127,
+      "step": 695
+    },
+    {
+      "epoch": 2.147013782542113,
+      "grad_norm": 0.7254396412798532,
+      "learning_rate": 1.4084966151816124e-05,
+      "loss": 0.7071,
+      "step": 700
+    },
+    {
+      "epoch": 2.147013782542113,
+      "eval_loss": 0.8550077676773071,
+      "eval_runtime": 3.8848,
+      "eval_samples_per_second": 31.919,
+      "eval_steps_per_second": 2.059,
+      "step": 700
+    },
+    {
+      "epoch": 2.1623277182235836,
+      "grad_norm": 0.73349139216254,
+      "learning_rate": 1.3986999710601348e-05,
+      "loss": 0.7298,
+      "step": 705
+    },
+    {
+      "epoch": 2.1776416539050536,
+      "grad_norm": 0.6655753573647281,
+      "learning_rate": 1.3888576158482586e-05,
+      "loss": 0.7124,
+      "step": 710
+    },
+    {
+      "epoch": 2.1929555895865236,
+      "grad_norm": 0.6987464871327375,
+      "learning_rate": 1.3789706779754326e-05,
+      "loss": 0.712,
+      "step": 715
+    },
+    {
+      "epoch": 2.208269525267994,
+      "grad_norm": 0.7104463485359258,
+      "learning_rate": 1.3690402909825245e-05,
+      "loss": 0.7256,
+      "step": 720
+    },
+    {
+      "epoch": 2.223583460949464,
+      "grad_norm": 0.786597658435966,
+      "learning_rate": 1.3590675933918578e-05,
+      "loss": 0.7265,
+      "step": 725
+    },
+    {
+      "epoch": 2.238897396630934,
+      "grad_norm": 0.7359585689347169,
+      "learning_rate": 1.3490537285766809e-05,
+      "loss": 0.7167,
+      "step": 730
+    },
+    {
+      "epoch": 2.2542113323124044,
+      "grad_norm": 0.6905264840508457,
+      "learning_rate": 1.3389998446300791e-05,
+      "loss": 0.7046,
+      "step": 735
+    },
+    {
+      "epoch": 2.2695252679938744,
+      "grad_norm": 0.7110824744193723,
+      "learning_rate": 1.3289070942333448e-05,
+      "loss": 0.7113,
+      "step": 740
+    },
+    {
+      "epoch": 2.2848392036753444,
+      "grad_norm": 0.774570053362907,
+      "learning_rate": 1.3187766345238222e-05,
+      "loss": 0.7097,
+      "step": 745
+    },
+    {
+      "epoch": 2.300153139356815,
+      "grad_norm": 0.7178949231829396,
+      "learning_rate": 1.308609626962242e-05,
+      "loss": 0.6951,
+      "step": 750
+    },
+    {
+      "epoch": 2.315467075038285,
+      "grad_norm": 0.6778307950742112,
+      "learning_rate": 1.2984072371995581e-05,
+      "loss": 0.7119,
+      "step": 755
+    },
+    {
+      "epoch": 2.330781010719755,
+      "grad_norm": 0.7381317901698428,
+      "learning_rate": 1.288170634943307e-05,
+      "loss": 0.7179,
+      "step": 760
+    },
+    {
+      "epoch": 2.3460949464012253,
+      "grad_norm": 0.688339196574423,
+      "learning_rate": 1.2779009938234986e-05,
+      "loss": 0.7372,
+      "step": 765
+    },
+    {
+      "epoch": 2.3614088820826953,
+      "grad_norm": 0.7309911889901869,
+      "learning_rate": 1.2675994912580601e-05,
+      "loss": 0.7217,
+      "step": 770
+    },
+    {
+      "epoch": 2.3767228177641653,
+      "grad_norm": 2.627453466768546,
+      "learning_rate": 1.2572673083178448e-05,
+      "loss": 0.7208,
+      "step": 775
+    },
+    {
+      "epoch": 2.3920367534456357,
+      "grad_norm": 0.6825595176377366,
+      "learning_rate": 1.2469056295912216e-05,
+      "loss": 0.7173,
+      "step": 780
+    },
+    {
+      "epoch": 2.4073506891271057,
+      "grad_norm": 0.681764187496552,
+      "learning_rate": 1.2365156430482621e-05,
+      "loss": 0.7172,
+      "step": 785
+    },
+    {
+      "epoch": 2.4226646248085757,
+      "grad_norm": 0.6957949104606218,
+      "learning_rate": 1.2260985399045379e-05,
+      "loss": 0.7144,
+      "step": 790
+    },
+    {
+      "epoch": 2.437978560490046,
+      "grad_norm": 0.6810069800053375,
+      "learning_rate": 1.2156555144845489e-05,
+      "loss": 0.7153,
+      "step": 795
+    },
+    {
+      "epoch": 2.453292496171516,
+      "grad_norm": 0.6879227501131829,
+      "learning_rate": 1.2051877640847929e-05,
+      "loss": 0.7208,
+      "step": 800
+    },
+    {
+      "epoch": 2.453292496171516,
+      "eval_loss": 0.8501381278038025,
+      "eval_runtime": 3.7489,
+      "eval_samples_per_second": 33.076,
+      "eval_steps_per_second": 2.134,
+      "step": 800
+    },
+    {
+      "epoch": 2.468606431852986,
+      "grad_norm": 0.7074177591745171,
+      "learning_rate": 1.1946964888364949e-05,
+      "loss": 0.7293,
+      "step": 805
+    },
+    {
+      "epoch": 2.4839203675344566,
+      "grad_norm": 0.7100957198483567,
+      "learning_rate": 1.1841828915680127e-05,
+      "loss": 0.7088,
+      "step": 810
+    },
+    {
+      "epoch": 2.4992343032159265,
+      "grad_norm": 0.7065376294005609,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.7083,
+      "step": 815
+    },
+    {
+      "epoch": 2.5145482388973965,
+      "grad_norm": 0.699699294689246,
+      "learning_rate": 1.1630935549418627e-05,
+      "loss": 0.7239,
+      "step": 820
+    },
+    {
+      "epoch": 2.5298621745788665,
+      "grad_norm": 0.6931742613638052,
+      "learning_rate": 1.1525202334839771e-05,
+      "loss": 0.7257,
+      "step": 825
+    },
+    {
+      "epoch": 2.545176110260337,
+      "grad_norm": 0.6626821835687099,
+      "learning_rate": 1.1419294255282574e-05,
+      "loss": 0.7158,
+      "step": 830
+    },
+    {
+      "epoch": 2.560490045941807,
+      "grad_norm": 0.7476424454423357,
+      "learning_rate": 1.1313223453145202e-05,
+      "loss": 0.7231,
+      "step": 835
+    },
+    {
+      "epoch": 2.5758039816232774,
+      "grad_norm": 0.7121987313639168,
+      "learning_rate": 1.1207002089482026e-05,
+      "loss": 0.7272,
+      "step": 840
+    },
+    {
+      "epoch": 2.5911179173047474,
+      "grad_norm": 0.6842806839970864,
+      "learning_rate": 1.1100642342609352e-05,
+      "loss": 0.7215,
+      "step": 845
+    },
+    {
+      "epoch": 2.6064318529862174,
+      "grad_norm": 0.671282856198737,
+      "learning_rate": 1.0994156406709155e-05,
+      "loss": 0.7086,
+      "step": 850
+    },
+    {
+      "epoch": 2.6217457886676874,
+      "grad_norm": 0.7127796423271462,
+      "learning_rate": 1.088755649043104e-05,
+      "loss": 0.7113,
+      "step": 855
+    },
+    {
+      "epoch": 2.637059724349158,
+      "grad_norm": 0.6642491628332302,
+      "learning_rate": 1.0780854815492496e-05,
+      "loss": 0.7247,
+      "step": 860
+    },
+    {
+      "epoch": 2.652373660030628,
+      "grad_norm": 0.6698942933482407,
+      "learning_rate": 1.0674063615277681e-05,
+      "loss": 0.7301,
+      "step": 865
+    },
+    {
+      "epoch": 2.6676875957120982,
+      "grad_norm": 0.6690575090698347,
+      "learning_rate": 1.0567195133434851e-05,
+      "loss": 0.7318,
+      "step": 870
+    },
+    {
+      "epoch": 2.6830015313935682,
+      "grad_norm": 0.6647266330654462,
+      "learning_rate": 1.0460261622472631e-05,
+      "loss": 0.7143,
+      "step": 875
+    },
+    {
+      "epoch": 2.698315467075038,
+      "grad_norm": 0.6879144621587469,
+      "learning_rate": 1.0353275342355262e-05,
+      "loss": 0.7227,
+      "step": 880
+    },
+    {
+      "epoch": 2.713629402756508,
+      "grad_norm": 0.6775051673571305,
+      "learning_rate": 1.024624855909698e-05,
+      "loss": 0.715,
+      "step": 885
+    },
+    {
+      "epoch": 2.7289433384379786,
+      "grad_norm": 0.6785052740842338,
+      "learning_rate": 1.013919354335572e-05,
+      "loss": 0.7224,
+      "step": 890
+    },
+    {
+      "epoch": 2.7442572741194486,
+      "grad_norm": 0.6852717568024729,
+      "learning_rate": 1.0032122569026284e-05,
+      "loss": 0.7181,
+      "step": 895
+    },
+    {
+      "epoch": 2.759571209800919,
+      "grad_norm": 0.6966758449578118,
+      "learning_rate": 9.925047911833137e-06,
+      "loss": 0.726,
+      "step": 900
+    },
+    {
+      "epoch": 2.759571209800919,
+      "eval_loss": 0.8449206352233887,
+      "eval_runtime": 3.7457,
+      "eval_samples_per_second": 33.104,
+      "eval_steps_per_second": 2.136,
+      "step": 900
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1630,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 95696971628544.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-900/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8128bba117ecebe610aa8a93374390d0c029e4632d49ee23fa1bd8e6b39d6679
+size 7352

checkpoints/checkpoint-900/zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import json
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``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``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``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``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        state_dict_split = split_torch_state_dict_into_shards(state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``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``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)