Upload folder using huggingface_hub
Browse files- config.json +32 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +53 -0
- trainer_state.json +634 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_ctx": 512,
|
| 14 |
+
"n_embd": 512,
|
| 15 |
+
"n_head": 8,
|
| 16 |
+
"n_inner": null,
|
| 17 |
+
"n_layer": 6,
|
| 18 |
+
"n_positions": 512,
|
| 19 |
+
"reorder_and_upcast_attn": false,
|
| 20 |
+
"resid_pdrop": 0.1,
|
| 21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 22 |
+
"scale_attn_weights": true,
|
| 23 |
+
"summary_activation": null,
|
| 24 |
+
"summary_first_dropout": 0.1,
|
| 25 |
+
"summary_proj_to_labels": true,
|
| 26 |
+
"summary_type": "cls_index",
|
| 27 |
+
"summary_use_proj": true,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.52.3",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 50257
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.52.3"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c97967e7892ee92c3125cfb5fcc7973cb4866d5be9d315dce5056853368efbd
|
| 3 |
+
size 179643784
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a732cc857dacb756641184afa2add289ad5143a461ed696b8268a23f21a260d
|
| 3 |
+
size 359336314
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f0905a2ca2884b688f260ec79576f47723236ac25d6f8f69a3c3d85cbc1b71c
|
| 3 |
+
size 14244
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59a4acfb0da74c479080613978839dd3cbb4608fd2c07e764b4c844401d8dd5f
|
| 3 |
+
size 988
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e88b9a7c20d0a7e67be23b50c7564265c79690a0db9c7737ff1c025326cda20a
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"mask_token": {
|
| 17 |
+
"content": "<mask>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"pad_token": {
|
| 24 |
+
"content": "<pad>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "<unk>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"eos_token": "</s>",
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "<mask>",
|
| 49 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
+
"pad_token": "<pad>",
|
| 51 |
+
"tokenizer_class": "PreTrainedTokenizer",
|
| 52 |
+
"unk_token": "<unk>"
|
| 53 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,634 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 4000,
|
| 3 |
+
"best_metric": 6.2553181648254395,
|
| 4 |
+
"best_model_checkpoint": "gpt-small-c4/checkpoint-4000",
|
| 5 |
+
"epoch": 0.20065211938801103,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 4000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.005016302984700276,
|
| 14 |
+
"grad_norm": 1.367209553718567,
|
| 15 |
+
"learning_rate": 4.975169300225734e-05,
|
| 16 |
+
"loss": 8.9927,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.005016302984700276,
|
| 21 |
+
"eval_loss": 8.038568496704102,
|
| 22 |
+
"eval_runtime": 106.068,
|
| 23 |
+
"eval_samples_per_second": 167.619,
|
| 24 |
+
"eval_steps_per_second": 20.958,
|
| 25 |
+
"step": 100
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.010032605969400551,
|
| 29 |
+
"grad_norm": 1.294573426246643,
|
| 30 |
+
"learning_rate": 4.950087785302233e-05,
|
| 31 |
+
"loss": 7.6182,
|
| 32 |
+
"step": 200
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.010032605969400551,
|
| 36 |
+
"eval_loss": 7.498734474182129,
|
| 37 |
+
"eval_runtime": 102.098,
|
| 38 |
+
"eval_samples_per_second": 174.137,
|
| 39 |
+
"eval_steps_per_second": 21.773,
|
| 40 |
+
"step": 200
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.015048908954100828,
|
| 44 |
+
"grad_norm": 1.3138136863708496,
|
| 45 |
+
"learning_rate": 4.925006270378731e-05,
|
| 46 |
+
"loss": 7.4073,
|
| 47 |
+
"step": 300
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.015048908954100828,
|
| 51 |
+
"eval_loss": 7.337331295013428,
|
| 52 |
+
"eval_runtime": 93.9798,
|
| 53 |
+
"eval_samples_per_second": 189.179,
|
| 54 |
+
"eval_steps_per_second": 23.654,
|
| 55 |
+
"step": 300
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.020065211938801102,
|
| 59 |
+
"grad_norm": 1.247786283493042,
|
| 60 |
+
"learning_rate": 4.89992475545523e-05,
|
| 61 |
+
"loss": 7.2394,
|
| 62 |
+
"step": 400
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.020065211938801102,
|
| 66 |
+
"eval_loss": 7.221430778503418,
|
| 67 |
+
"eval_runtime": 94.4305,
|
| 68 |
+
"eval_samples_per_second": 188.276,
|
| 69 |
+
"eval_steps_per_second": 23.541,
|
| 70 |
+
"step": 400
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.02508151492350138,
|
| 74 |
+
"grad_norm": 1.5004276037216187,
|
| 75 |
+
"learning_rate": 4.874843240531728e-05,
|
| 76 |
+
"loss": 7.1744,
|
| 77 |
+
"step": 500
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.02508151492350138,
|
| 81 |
+
"eval_loss": 7.13123893737793,
|
| 82 |
+
"eval_runtime": 93.9964,
|
| 83 |
+
"eval_samples_per_second": 189.146,
|
| 84 |
+
"eval_steps_per_second": 23.65,
|
| 85 |
+
"step": 500
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.030097817908201655,
|
| 89 |
+
"grad_norm": 1.6555237770080566,
|
| 90 |
+
"learning_rate": 4.8497617256082266e-05,
|
| 91 |
+
"loss": 7.0923,
|
| 92 |
+
"step": 600
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.030097817908201655,
|
| 96 |
+
"eval_loss": 7.061245918273926,
|
| 97 |
+
"eval_runtime": 94.3719,
|
| 98 |
+
"eval_samples_per_second": 188.393,
|
| 99 |
+
"eval_steps_per_second": 23.556,
|
| 100 |
+
"step": 600
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.03511412089290193,
|
| 104 |
+
"grad_norm": 1.7525192499160767,
|
| 105 |
+
"learning_rate": 4.8246802106847256e-05,
|
| 106 |
+
"loss": 7.0225,
|
| 107 |
+
"step": 700
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.03511412089290193,
|
| 111 |
+
"eval_loss": 6.9907097816467285,
|
| 112 |
+
"eval_runtime": 94.5022,
|
| 113 |
+
"eval_samples_per_second": 188.133,
|
| 114 |
+
"eval_steps_per_second": 23.523,
|
| 115 |
+
"step": 700
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.040130423877602205,
|
| 119 |
+
"grad_norm": 1.6555861234664917,
|
| 120 |
+
"learning_rate": 4.7995986957612246e-05,
|
| 121 |
+
"loss": 6.9318,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.040130423877602205,
|
| 126 |
+
"eval_loss": 6.9372453689575195,
|
| 127 |
+
"eval_runtime": 94.1339,
|
| 128 |
+
"eval_samples_per_second": 188.869,
|
| 129 |
+
"eval_steps_per_second": 23.615,
|
| 130 |
+
"step": 800
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.045146726862302484,
|
| 134 |
+
"grad_norm": 2.0145726203918457,
|
| 135 |
+
"learning_rate": 4.774517180837723e-05,
|
| 136 |
+
"loss": 6.8885,
|
| 137 |
+
"step": 900
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.045146726862302484,
|
| 141 |
+
"eval_loss": 6.890288352966309,
|
| 142 |
+
"eval_runtime": 94.637,
|
| 143 |
+
"eval_samples_per_second": 187.865,
|
| 144 |
+
"eval_steps_per_second": 23.49,
|
| 145 |
+
"step": 900
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.05016302984700276,
|
| 149 |
+
"grad_norm": 1.4140468835830688,
|
| 150 |
+
"learning_rate": 4.749435665914221e-05,
|
| 151 |
+
"loss": 6.8442,
|
| 152 |
+
"step": 1000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.05016302984700276,
|
| 156 |
+
"eval_loss": 6.846121788024902,
|
| 157 |
+
"eval_runtime": 98.5415,
|
| 158 |
+
"eval_samples_per_second": 180.421,
|
| 159 |
+
"eval_steps_per_second": 22.559,
|
| 160 |
+
"step": 1000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.05517933283170304,
|
| 164 |
+
"grad_norm": 2.1040637493133545,
|
| 165 |
+
"learning_rate": 4.72435415099072e-05,
|
| 166 |
+
"loss": 6.7646,
|
| 167 |
+
"step": 1100
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.05517933283170304,
|
| 171 |
+
"eval_loss": 6.808917999267578,
|
| 172 |
+
"eval_runtime": 95.1845,
|
| 173 |
+
"eval_samples_per_second": 186.785,
|
| 174 |
+
"eval_steps_per_second": 23.355,
|
| 175 |
+
"step": 1100
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.06019563581640331,
|
| 179 |
+
"grad_norm": 1.9216736555099487,
|
| 180 |
+
"learning_rate": 4.6992726360672185e-05,
|
| 181 |
+
"loss": 6.7815,
|
| 182 |
+
"step": 1200
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.06019563581640331,
|
| 186 |
+
"eval_loss": 6.7738037109375,
|
| 187 |
+
"eval_runtime": 94.6149,
|
| 188 |
+
"eval_samples_per_second": 187.909,
|
| 189 |
+
"eval_steps_per_second": 23.495,
|
| 190 |
+
"step": 1200
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.06521193880110358,
|
| 194 |
+
"grad_norm": 1.5636332035064697,
|
| 195 |
+
"learning_rate": 4.6741911211437175e-05,
|
| 196 |
+
"loss": 6.7469,
|
| 197 |
+
"step": 1300
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.06521193880110358,
|
| 201 |
+
"eval_loss": 6.739809036254883,
|
| 202 |
+
"eval_runtime": 94.7876,
|
| 203 |
+
"eval_samples_per_second": 187.567,
|
| 204 |
+
"eval_steps_per_second": 23.452,
|
| 205 |
+
"step": 1300
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.07022824178580386,
|
| 209 |
+
"grad_norm": 1.5623961687088013,
|
| 210 |
+
"learning_rate": 4.649109606220216e-05,
|
| 211 |
+
"loss": 6.7202,
|
| 212 |
+
"step": 1400
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.07022824178580386,
|
| 216 |
+
"eval_loss": 6.719963550567627,
|
| 217 |
+
"eval_runtime": 94.3193,
|
| 218 |
+
"eval_samples_per_second": 188.498,
|
| 219 |
+
"eval_steps_per_second": 23.569,
|
| 220 |
+
"step": 1400
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.07524454477050414,
|
| 224 |
+
"grad_norm": 1.5444605350494385,
|
| 225 |
+
"learning_rate": 4.624028091296714e-05,
|
| 226 |
+
"loss": 6.689,
|
| 227 |
+
"step": 1500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.07524454477050414,
|
| 231 |
+
"eval_loss": 6.685614109039307,
|
| 232 |
+
"eval_runtime": 94.1801,
|
| 233 |
+
"eval_samples_per_second": 188.777,
|
| 234 |
+
"eval_steps_per_second": 23.604,
|
| 235 |
+
"step": 1500
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.08026084775520441,
|
| 239 |
+
"grad_norm": 2.0542852878570557,
|
| 240 |
+
"learning_rate": 4.598946576373213e-05,
|
| 241 |
+
"loss": 6.6448,
|
| 242 |
+
"step": 1600
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.08026084775520441,
|
| 246 |
+
"eval_loss": 6.665727615356445,
|
| 247 |
+
"eval_runtime": 94.8119,
|
| 248 |
+
"eval_samples_per_second": 187.519,
|
| 249 |
+
"eval_steps_per_second": 23.446,
|
| 250 |
+
"step": 1600
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.08527715073990469,
|
| 254 |
+
"grad_norm": 1.7234691381454468,
|
| 255 |
+
"learning_rate": 4.573865061449712e-05,
|
| 256 |
+
"loss": 6.6167,
|
| 257 |
+
"step": 1700
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.08527715073990469,
|
| 261 |
+
"eval_loss": 6.640410423278809,
|
| 262 |
+
"eval_runtime": 94.192,
|
| 263 |
+
"eval_samples_per_second": 188.753,
|
| 264 |
+
"eval_steps_per_second": 23.601,
|
| 265 |
+
"step": 1700
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.09029345372460497,
|
| 269 |
+
"grad_norm": 1.8299592733383179,
|
| 270 |
+
"learning_rate": 4.5487835465262104e-05,
|
| 271 |
+
"loss": 6.6109,
|
| 272 |
+
"step": 1800
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.09029345372460497,
|
| 276 |
+
"eval_loss": 6.620120525360107,
|
| 277 |
+
"eval_runtime": 93.7995,
|
| 278 |
+
"eval_samples_per_second": 189.543,
|
| 279 |
+
"eval_steps_per_second": 23.699,
|
| 280 |
+
"step": 1800
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.09530975670930525,
|
| 284 |
+
"grad_norm": 3.1380774974823,
|
| 285 |
+
"learning_rate": 4.523702031602709e-05,
|
| 286 |
+
"loss": 6.6401,
|
| 287 |
+
"step": 1900
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.09530975670930525,
|
| 291 |
+
"eval_loss": 6.596529006958008,
|
| 292 |
+
"eval_runtime": 94.29,
|
| 293 |
+
"eval_samples_per_second": 188.557,
|
| 294 |
+
"eval_steps_per_second": 23.576,
|
| 295 |
+
"step": 1900
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.10032605969400551,
|
| 299 |
+
"grad_norm": 2.301722526550293,
|
| 300 |
+
"learning_rate": 4.4986205166792077e-05,
|
| 301 |
+
"loss": 6.5718,
|
| 302 |
+
"step": 2000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.10032605969400551,
|
| 306 |
+
"eval_loss": 6.580358982086182,
|
| 307 |
+
"eval_runtime": 94.8156,
|
| 308 |
+
"eval_samples_per_second": 187.511,
|
| 309 |
+
"eval_steps_per_second": 23.445,
|
| 310 |
+
"step": 2000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.1053423626787058,
|
| 314 |
+
"grad_norm": 2.1571052074432373,
|
| 315 |
+
"learning_rate": 4.473539001755706e-05,
|
| 316 |
+
"loss": 6.5723,
|
| 317 |
+
"step": 2100
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.1053423626787058,
|
| 321 |
+
"eval_loss": 6.559490203857422,
|
| 322 |
+
"eval_runtime": 93.9805,
|
| 323 |
+
"eval_samples_per_second": 189.177,
|
| 324 |
+
"eval_steps_per_second": 23.654,
|
| 325 |
+
"step": 2100
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.11035866566340607,
|
| 329 |
+
"grad_norm": 1.8901225328445435,
|
| 330 |
+
"learning_rate": 4.448457486832205e-05,
|
| 331 |
+
"loss": 6.5405,
|
| 332 |
+
"step": 2200
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.11035866566340607,
|
| 336 |
+
"eval_loss": 6.536637783050537,
|
| 337 |
+
"eval_runtime": 95.7913,
|
| 338 |
+
"eval_samples_per_second": 185.601,
|
| 339 |
+
"eval_steps_per_second": 23.207,
|
| 340 |
+
"step": 2200
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.11537496864810634,
|
| 344 |
+
"grad_norm": 1.9951658248901367,
|
| 345 |
+
"learning_rate": 4.423375971908704e-05,
|
| 346 |
+
"loss": 6.5143,
|
| 347 |
+
"step": 2300
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.11537496864810634,
|
| 351 |
+
"eval_loss": 6.518816947937012,
|
| 352 |
+
"eval_runtime": 94.7754,
|
| 353 |
+
"eval_samples_per_second": 187.591,
|
| 354 |
+
"eval_steps_per_second": 23.455,
|
| 355 |
+
"step": 2300
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.12039127163280662,
|
| 359 |
+
"grad_norm": 1.5648778676986694,
|
| 360 |
+
"learning_rate": 4.398294456985202e-05,
|
| 361 |
+
"loss": 6.5145,
|
| 362 |
+
"step": 2400
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.12039127163280662,
|
| 366 |
+
"eval_loss": 6.496397018432617,
|
| 367 |
+
"eval_runtime": 119.6751,
|
| 368 |
+
"eval_samples_per_second": 148.561,
|
| 369 |
+
"eval_steps_per_second": 18.575,
|
| 370 |
+
"step": 2400
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.1254075746175069,
|
| 374 |
+
"grad_norm": 1.6384185552597046,
|
| 375 |
+
"learning_rate": 4.3732129420617006e-05,
|
| 376 |
+
"loss": 6.4635,
|
| 377 |
+
"step": 2500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.1254075746175069,
|
| 381 |
+
"eval_loss": 6.48058557510376,
|
| 382 |
+
"eval_runtime": 116.6468,
|
| 383 |
+
"eval_samples_per_second": 152.417,
|
| 384 |
+
"eval_steps_per_second": 19.058,
|
| 385 |
+
"step": 2500
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.13042387760220717,
|
| 389 |
+
"grad_norm": 2.172386884689331,
|
| 390 |
+
"learning_rate": 4.3481314271381995e-05,
|
| 391 |
+
"loss": 6.4973,
|
| 392 |
+
"step": 2600
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.13042387760220717,
|
| 396 |
+
"eval_loss": 6.466433048248291,
|
| 397 |
+
"eval_runtime": 98.1503,
|
| 398 |
+
"eval_samples_per_second": 181.141,
|
| 399 |
+
"eval_steps_per_second": 22.649,
|
| 400 |
+
"step": 2600
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.13544018058690746,
|
| 404 |
+
"grad_norm": 1.9169673919677734,
|
| 405 |
+
"learning_rate": 4.323049912214698e-05,
|
| 406 |
+
"loss": 6.475,
|
| 407 |
+
"step": 2700
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.13544018058690746,
|
| 411 |
+
"eval_loss": 6.4444684982299805,
|
| 412 |
+
"eval_runtime": 94.3642,
|
| 413 |
+
"eval_samples_per_second": 188.408,
|
| 414 |
+
"eval_steps_per_second": 23.558,
|
| 415 |
+
"step": 2700
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.14045648357160773,
|
| 419 |
+
"grad_norm": 1.8222382068634033,
|
| 420 |
+
"learning_rate": 4.297968397291197e-05,
|
| 421 |
+
"loss": 6.4216,
|
| 422 |
+
"step": 2800
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.14045648357160773,
|
| 426 |
+
"eval_loss": 6.434403896331787,
|
| 427 |
+
"eval_runtime": 96.3492,
|
| 428 |
+
"eval_samples_per_second": 184.527,
|
| 429 |
+
"eval_steps_per_second": 23.072,
|
| 430 |
+
"step": 2800
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.145472786556308,
|
| 434 |
+
"grad_norm": 2.0480902194976807,
|
| 435 |
+
"learning_rate": 4.272886882367695e-05,
|
| 436 |
+
"loss": 6.4062,
|
| 437 |
+
"step": 2900
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.145472786556308,
|
| 441 |
+
"eval_loss": 6.415233135223389,
|
| 442 |
+
"eval_runtime": 94.0684,
|
| 443 |
+
"eval_samples_per_second": 189.001,
|
| 444 |
+
"eval_steps_per_second": 23.632,
|
| 445 |
+
"step": 2900
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.1504890895410083,
|
| 449 |
+
"grad_norm": 1.965072512626648,
|
| 450 |
+
"learning_rate": 4.2478053674441935e-05,
|
| 451 |
+
"loss": 6.3655,
|
| 452 |
+
"step": 3000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.1504890895410083,
|
| 456 |
+
"eval_loss": 6.401170253753662,
|
| 457 |
+
"eval_runtime": 94.0417,
|
| 458 |
+
"eval_samples_per_second": 189.054,
|
| 459 |
+
"eval_steps_per_second": 23.638,
|
| 460 |
+
"step": 3000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.15550539252570855,
|
| 464 |
+
"grad_norm": 2.16786789894104,
|
| 465 |
+
"learning_rate": 4.2227238525206924e-05,
|
| 466 |
+
"loss": 6.4038,
|
| 467 |
+
"step": 3100
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.15550539252570855,
|
| 471 |
+
"eval_loss": 6.388797283172607,
|
| 472 |
+
"eval_runtime": 93.9464,
|
| 473 |
+
"eval_samples_per_second": 189.246,
|
| 474 |
+
"eval_steps_per_second": 23.662,
|
| 475 |
+
"step": 3100
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.16052169551040882,
|
| 479 |
+
"grad_norm": 2.5082712173461914,
|
| 480 |
+
"learning_rate": 4.1976423375971914e-05,
|
| 481 |
+
"loss": 6.3553,
|
| 482 |
+
"step": 3200
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.16052169551040882,
|
| 486 |
+
"eval_loss": 6.368188858032227,
|
| 487 |
+
"eval_runtime": 94.1089,
|
| 488 |
+
"eval_samples_per_second": 188.919,
|
| 489 |
+
"eval_steps_per_second": 23.622,
|
| 490 |
+
"step": 3200
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.1655379984951091,
|
| 494 |
+
"grad_norm": 2.0116617679595947,
|
| 495 |
+
"learning_rate": 4.17256082267369e-05,
|
| 496 |
+
"loss": 6.3573,
|
| 497 |
+
"step": 3300
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.1655379984951091,
|
| 501 |
+
"eval_loss": 6.35645866394043,
|
| 502 |
+
"eval_runtime": 94.2829,
|
| 503 |
+
"eval_samples_per_second": 188.571,
|
| 504 |
+
"eval_steps_per_second": 23.578,
|
| 505 |
+
"step": 3300
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.17055430147980938,
|
| 509 |
+
"grad_norm": 2.309736728668213,
|
| 510 |
+
"learning_rate": 4.147479307750188e-05,
|
| 511 |
+
"loss": 6.3458,
|
| 512 |
+
"step": 3400
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.17055430147980938,
|
| 516 |
+
"eval_loss": 6.339991092681885,
|
| 517 |
+
"eval_runtime": 94.4661,
|
| 518 |
+
"eval_samples_per_second": 188.205,
|
| 519 |
+
"eval_steps_per_second": 23.532,
|
| 520 |
+
"step": 3400
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.17557060446450964,
|
| 524 |
+
"grad_norm": 1.963045597076416,
|
| 525 |
+
"learning_rate": 4.122397792826687e-05,
|
| 526 |
+
"loss": 6.3157,
|
| 527 |
+
"step": 3500
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.17557060446450964,
|
| 531 |
+
"eval_loss": 6.325737476348877,
|
| 532 |
+
"eval_runtime": 94.2601,
|
| 533 |
+
"eval_samples_per_second": 188.616,
|
| 534 |
+
"eval_steps_per_second": 23.584,
|
| 535 |
+
"step": 3500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.18058690744920994,
|
| 539 |
+
"grad_norm": 2.3348584175109863,
|
| 540 |
+
"learning_rate": 4.0973162779031853e-05,
|
| 541 |
+
"loss": 6.3232,
|
| 542 |
+
"step": 3600
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.18058690744920994,
|
| 546 |
+
"eval_loss": 6.314403533935547,
|
| 547 |
+
"eval_runtime": 94.6269,
|
| 548 |
+
"eval_samples_per_second": 187.885,
|
| 549 |
+
"eval_steps_per_second": 23.492,
|
| 550 |
+
"step": 3600
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.1856032104339102,
|
| 554 |
+
"grad_norm": 1.7809332609176636,
|
| 555 |
+
"learning_rate": 4.072234762979684e-05,
|
| 556 |
+
"loss": 6.2809,
|
| 557 |
+
"step": 3700
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.1856032104339102,
|
| 561 |
+
"eval_loss": 6.2983903884887695,
|
| 562 |
+
"eval_runtime": 94.2727,
|
| 563 |
+
"eval_samples_per_second": 188.591,
|
| 564 |
+
"eval_steps_per_second": 23.581,
|
| 565 |
+
"step": 3700
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.1906195134186105,
|
| 569 |
+
"grad_norm": 2.0216691493988037,
|
| 570 |
+
"learning_rate": 4.047153248056183e-05,
|
| 571 |
+
"loss": 6.2558,
|
| 572 |
+
"step": 3800
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.1906195134186105,
|
| 576 |
+
"eval_loss": 6.28033971786499,
|
| 577 |
+
"eval_runtime": 94.2314,
|
| 578 |
+
"eval_samples_per_second": 188.674,
|
| 579 |
+
"eval_steps_per_second": 23.591,
|
| 580 |
+
"step": 3800
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.19563581640331076,
|
| 584 |
+
"grad_norm": 2.2930386066436768,
|
| 585 |
+
"learning_rate": 4.022071733132681e-05,
|
| 586 |
+
"loss": 6.2869,
|
| 587 |
+
"step": 3900
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.19563581640331076,
|
| 591 |
+
"eval_loss": 6.2675676345825195,
|
| 592 |
+
"eval_runtime": 94.5425,
|
| 593 |
+
"eval_samples_per_second": 188.053,
|
| 594 |
+
"eval_steps_per_second": 23.513,
|
| 595 |
+
"step": 3900
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 0.20065211938801103,
|
| 599 |
+
"grad_norm": 2.321624755859375,
|
| 600 |
+
"learning_rate": 3.99699021820918e-05,
|
| 601 |
+
"loss": 6.2825,
|
| 602 |
+
"step": 4000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.20065211938801103,
|
| 606 |
+
"eval_loss": 6.2553181648254395,
|
| 607 |
+
"eval_runtime": 94.2273,
|
| 608 |
+
"eval_samples_per_second": 188.682,
|
| 609 |
+
"eval_steps_per_second": 23.592,
|
| 610 |
+
"step": 4000
|
| 611 |
+
}
|
| 612 |
+
],
|
| 613 |
+
"logging_steps": 100,
|
| 614 |
+
"max_steps": 19935,
|
| 615 |
+
"num_input_tokens_seen": 0,
|
| 616 |
+
"num_train_epochs": 1,
|
| 617 |
+
"save_steps": 100,
|
| 618 |
+
"stateful_callbacks": {
|
| 619 |
+
"TrainerControl": {
|
| 620 |
+
"args": {
|
| 621 |
+
"should_epoch_stop": false,
|
| 622 |
+
"should_evaluate": false,
|
| 623 |
+
"should_log": false,
|
| 624 |
+
"should_save": true,
|
| 625 |
+
"should_training_stop": false
|
| 626 |
+
},
|
| 627 |
+
"attributes": {}
|
| 628 |
+
}
|
| 629 |
+
},
|
| 630 |
+
"total_flos": 929726201856000.0,
|
| 631 |
+
"train_batch_size": 8,
|
| 632 |
+
"trial_name": null,
|
| 633 |
+
"trial_params": null
|
| 634 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:816cd880c2d6abfb50dbc2582892848cac9e4eab6906857c70c52f7f8bdb136c
|
| 3 |
+
size 5240
|