Delete gpt2cocoSAD
Browse files- gpt2cocoSAD/model_SAD/checkpoint/added_tokens.json +0 -4
- gpt2cocoSAD/model_SAD/checkpoint/config.json +0 -40
- gpt2cocoSAD/model_SAD/checkpoint/generation_config.json +0 -9
- gpt2cocoSAD/model_SAD/checkpoint/merges.txt +0 -0
- gpt2cocoSAD/model_SAD/checkpoint/model.safetensors +0 -3
- gpt2cocoSAD/model_SAD/checkpoint/optimizer.pt +0 -3
- gpt2cocoSAD/model_SAD/checkpoint/rng_state_0.pth +0 -3
- gpt2cocoSAD/model_SAD/checkpoint/rng_state_1.pth +0 -3
- gpt2cocoSAD/model_SAD/checkpoint/rng_state_2.pth +0 -3
- gpt2cocoSAD/model_SAD/checkpoint/rng_state_3.pth +0 -3
- gpt2cocoSAD/model_SAD/checkpoint/rng_state_4.pth +0 -3
- gpt2cocoSAD/model_SAD/checkpoint/rng_state_5.pth +0 -3
- gpt2cocoSAD/model_SAD/checkpoint/rng_state_6.pth +0 -3
- gpt2cocoSAD/model_SAD/checkpoint/rng_state_7.pth +0 -3
- gpt2cocoSAD/model_SAD/checkpoint/scaler.pt +0 -3
- gpt2cocoSAD/model_SAD/checkpoint/scheduler.pt +0 -3
- gpt2cocoSAD/model_SAD/checkpoint/special_tokens_map.json +0 -37
- gpt2cocoSAD/model_SAD/checkpoint/tokenizer_config.json +0 -40
- gpt2cocoSAD/model_SAD/checkpoint/trainer_state.json +0 -3499
- gpt2cocoSAD/model_SAD/checkpoint/training_args.bin +0 -3
- gpt2cocoSAD/model_SAD/checkpoint/vocab.json +0 -0
- gpt2cocoSAD/tokenized_data_SAD/dataset_dict.json +0 -1
- gpt2cocoSAD/tokenized_data_SAD/test/data-00000-of-00001.arrow +0 -3
- gpt2cocoSAD/tokenized_data_SAD/test/dataset_info.json +0 -49
- gpt2cocoSAD/tokenized_data_SAD/test/state.json +0 -22
- gpt2cocoSAD/tokenized_data_SAD/train/data-00000-of-00001.arrow +0 -3
- gpt2cocoSAD/tokenized_data_SAD/train/dataset_info.json +0 -49
- gpt2cocoSAD/tokenized_data_SAD/train/state.json +0 -22
gpt2cocoSAD/model_SAD/checkpoint/added_tokens.json
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"<pad>": 50258,
|
| 3 |
-
"<|startoftext|>": 50257
|
| 4 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/config.json
DELETED
|
@@ -1,40 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"activation_function": "gelu_new",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"GPT2LMHeadModel"
|
| 5 |
-
],
|
| 6 |
-
"attn_pdrop": 0.1,
|
| 7 |
-
"bos_token_id": 50256,
|
| 8 |
-
"cls_token_id": 50257,
|
| 9 |
-
"dtype": "float32",
|
| 10 |
-
"embd_pdrop": 0.1,
|
| 11 |
-
"eos_token_id": 50256,
|
| 12 |
-
"initializer_range": 0.02,
|
| 13 |
-
"layer_norm_epsilon": 1e-05,
|
| 14 |
-
"model_type": "gpt2",
|
| 15 |
-
"n_ctx": 1024,
|
| 16 |
-
"n_embd": 768,
|
| 17 |
-
"n_head": 12,
|
| 18 |
-
"n_inner": null,
|
| 19 |
-
"n_layer": 12,
|
| 20 |
-
"n_positions": 1024,
|
| 21 |
-
"pad_token_id": 50258,
|
| 22 |
-
"reorder_and_upcast_attn": false,
|
| 23 |
-
"resid_pdrop": 0.1,
|
| 24 |
-
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
-
"scale_attn_weights": true,
|
| 26 |
-
"summary_activation": null,
|
| 27 |
-
"summary_first_dropout": 0.1,
|
| 28 |
-
"summary_proj_to_labels": true,
|
| 29 |
-
"summary_type": "cls_index",
|
| 30 |
-
"summary_use_proj": true,
|
| 31 |
-
"task_specific_params": {
|
| 32 |
-
"text-generation": {
|
| 33 |
-
"do_sample": true,
|
| 34 |
-
"max_length": 50
|
| 35 |
-
}
|
| 36 |
-
},
|
| 37 |
-
"transformers_version": "4.57.1",
|
| 38 |
-
"use_cache": true,
|
| 39 |
-
"vocab_size": 50259
|
| 40 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/generation_config.json
DELETED
|
@@ -1,9 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"bos_token_id": 50256,
|
| 4 |
-
"eos_token_id": [
|
| 5 |
-
50256
|
| 6 |
-
],
|
| 7 |
-
"pad_token_id": 50258,
|
| 8 |
-
"transformers_version": "4.57.1"
|
| 9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:83d7ea52920f80121594d61fd152d1c622fc6281af37054c33380b081b2ef277
|
| 3 |
-
size 497780352
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:7ca6a6f8edba573904f208a82a8a5a807be4eccb032727fcd9833d4f6cc58be9
|
| 3 |
-
size 995654586
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/rng_state_0.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:aebbbdd9f6b6458006140b9399df973322b39193c3491688f309b28eda7f6516
|
| 3 |
-
size 15984
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/rng_state_1.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:02092b11072872275f41067881e0ff9c3ebb4f71cf3347a14575ee0c3bb4dc37
|
| 3 |
-
size 15984
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/rng_state_2.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:834873e0297393e1fa57f1b955d4a9198d35ae71d5b1b5b0661327390e456a6a
|
| 3 |
-
size 15984
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/rng_state_3.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6756722a563897612ae24bdf113ccc0f63bb646ff00b0de94943e7815ca03cf9
|
| 3 |
-
size 15984
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/rng_state_4.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:811a877d2d10d1034d381ef47c53f9a523828b58a68b612cd1b0858ee81e6c1e
|
| 3 |
-
size 15984
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/rng_state_5.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:65538c95dd42ed5ff89d120cad03ed208d8388db3902f5332493f3f25f8ac51a
|
| 3 |
-
size 15984
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/rng_state_6.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:44952594d0b6ac119c313df4062415014d62be491e303928f3548bb0f2c5c55f
|
| 3 |
-
size 15984
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/rng_state_7.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:2081cb2f3fdd83c5b77b31a5b51f1f3492a4f66d21e8c736d093ea56b1461995
|
| 3 |
-
size 15984
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/scaler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:52553f41dcf91d35bf246cc9a094ff932d32b1cb29717295de4846f5f25e9a11
|
| 3 |
-
size 988
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f86d4debfeccbc9cc7f34fa8036cc4f47e09cf0625bf34c4a4cb3f392bd25f62
|
| 3 |
-
size 1064
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/special_tokens_map.json
DELETED
|
@@ -1,37 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": {
|
| 3 |
-
"content": "<|endoftext|>",
|
| 4 |
-
"lstrip": false,
|
| 5 |
-
"normalized": true,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"cls_token": {
|
| 10 |
-
"content": "<|startoftext|>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"eos_token": {
|
| 17 |
-
"content": "<|endoftext|>",
|
| 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": "<|endoftext|>",
|
| 32 |
-
"lstrip": false,
|
| 33 |
-
"normalized": true,
|
| 34 |
-
"rstrip": false,
|
| 35 |
-
"single_word": false
|
| 36 |
-
}
|
| 37 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/tokenizer_config.json
DELETED
|
@@ -1,40 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
-
"add_prefix_space": false,
|
| 4 |
-
"added_tokens_decoder": {
|
| 5 |
-
"50256": {
|
| 6 |
-
"content": "<|endoftext|>",
|
| 7 |
-
"lstrip": false,
|
| 8 |
-
"normalized": false,
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false,
|
| 11 |
-
"special": true
|
| 12 |
-
},
|
| 13 |
-
"50257": {
|
| 14 |
-
"content": "<|startoftext|>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": false,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false,
|
| 19 |
-
"special": true
|
| 20 |
-
},
|
| 21 |
-
"50258": {
|
| 22 |
-
"content": "<pad>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": false,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false,
|
| 27 |
-
"special": true
|
| 28 |
-
}
|
| 29 |
-
},
|
| 30 |
-
"bos_token": "<|endoftext|>",
|
| 31 |
-
"clean_up_tokenization_spaces": false,
|
| 32 |
-
"cls_token": "<|startoftext|>",
|
| 33 |
-
"eos_token": "<|endoftext|>",
|
| 34 |
-
"errors": "replace",
|
| 35 |
-
"extra_special_tokens": {},
|
| 36 |
-
"model_max_length": 1024,
|
| 37 |
-
"pad_token": "<pad>",
|
| 38 |
-
"tokenizer_class": "GPT2Tokenizer",
|
| 39 |
-
"unk_token": "<|endoftext|>"
|
| 40 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/trainer_state.json
DELETED
|
@@ -1,3499 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": 900,
|
| 3 |
-
"best_metric": 2.5223655700683594,
|
| 4 |
-
"best_model_checkpoint": "../a1_text/fl/gpt2/pt3lgpt2coco/finetuned_on_pt3lgpt2coco_ICLR_rebuttal_prompt_pt3lgpt2coco_percent_0.01/checkpoint-900",
|
| 5 |
-
"epoch": 99.56896551724138,
|
| 6 |
-
"eval_steps": 100,
|
| 7 |
-
"global_step": 23100,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 0.43103448275862066,
|
| 14 |
-
"grad_norm": 0.3040359318256378,
|
| 15 |
-
"learning_rate": 0.00188,
|
| 16 |
-
"loss": 3.181,
|
| 17 |
-
"step": 100
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 0.43103448275862066,
|
| 21 |
-
"eval_loss": 2.6918227672576904,
|
| 22 |
-
"eval_runtime": 9.2125,
|
| 23 |
-
"eval_samples_per_second": 12846.835,
|
| 24 |
-
"eval_steps_per_second": 6.296,
|
| 25 |
-
"step": 100
|
| 26 |
-
},
|
| 27 |
-
{
|
| 28 |
-
"epoch": 0.8620689655172413,
|
| 29 |
-
"grad_norm": 0.3815867006778717,
|
| 30 |
-
"learning_rate": 0.0019999182861670534,
|
| 31 |
-
"loss": 2.675,
|
| 32 |
-
"step": 200
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"epoch": 0.8620689655172413,
|
| 36 |
-
"eval_loss": 2.596940517425537,
|
| 37 |
-
"eval_runtime": 9.249,
|
| 38 |
-
"eval_samples_per_second": 12796.027,
|
| 39 |
-
"eval_steps_per_second": 6.271,
|
| 40 |
-
"step": 200
|
| 41 |
-
},
|
| 42 |
-
{
|
| 43 |
-
"epoch": 1.293103448275862,
|
| 44 |
-
"grad_norm": 0.24237173795700073,
|
| 45 |
-
"learning_rate": 0.0019996519640898547,
|
| 46 |
-
"loss": 2.5393,
|
| 47 |
-
"step": 300
|
| 48 |
-
},
|
| 49 |
-
{
|
| 50 |
-
"epoch": 1.293103448275862,
|
| 51 |
-
"eval_loss": 2.5603010654449463,
|
| 52 |
-
"eval_runtime": 9.5083,
|
| 53 |
-
"eval_samples_per_second": 12447.149,
|
| 54 |
-
"eval_steps_per_second": 6.1,
|
| 55 |
-
"step": 300
|
| 56 |
-
},
|
| 57 |
-
{
|
| 58 |
-
"epoch": 1.7241379310344827,
|
| 59 |
-
"grad_norm": 0.22608302533626556,
|
| 60 |
-
"learning_rate": 0.0019992007500999214,
|
| 61 |
-
"loss": 2.5055,
|
| 62 |
-
"step": 400
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 1.7241379310344827,
|
| 66 |
-
"eval_loss": 2.5346174240112305,
|
| 67 |
-
"eval_runtime": 9.4684,
|
| 68 |
-
"eval_samples_per_second": 12499.57,
|
| 69 |
-
"eval_steps_per_second": 6.126,
|
| 70 |
-
"step": 400
|
| 71 |
-
},
|
| 72 |
-
{
|
| 73 |
-
"epoch": 2.1551724137931036,
|
| 74 |
-
"grad_norm": 0.21417607367038727,
|
| 75 |
-
"learning_rate": 0.001998564727652117,
|
| 76 |
-
"loss": 2.4472,
|
| 77 |
-
"step": 500
|
| 78 |
-
},
|
| 79 |
-
{
|
| 80 |
-
"epoch": 2.1551724137931036,
|
| 81 |
-
"eval_loss": 2.539055109024048,
|
| 82 |
-
"eval_runtime": 9.2538,
|
| 83 |
-
"eval_samples_per_second": 12789.421,
|
| 84 |
-
"eval_steps_per_second": 6.268,
|
| 85 |
-
"step": 500
|
| 86 |
-
},
|
| 87 |
-
{
|
| 88 |
-
"epoch": 2.586206896551724,
|
| 89 |
-
"grad_norm": 0.2077101767063141,
|
| 90 |
-
"learning_rate": 0.001997744014382789,
|
| 91 |
-
"loss": 2.392,
|
| 92 |
-
"step": 600
|
| 93 |
-
},
|
| 94 |
-
{
|
| 95 |
-
"epoch": 2.586206896551724,
|
| 96 |
-
"eval_loss": 2.5249011516571045,
|
| 97 |
-
"eval_runtime": 9.3812,
|
| 98 |
-
"eval_samples_per_second": 12615.75,
|
| 99 |
-
"eval_steps_per_second": 6.183,
|
| 100 |
-
"step": 600
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 3.0172413793103448,
|
| 104 |
-
"grad_norm": 0.2634534537792206,
|
| 105 |
-
"learning_rate": 0.0019967387620880147,
|
| 106 |
-
"loss": 2.4016,
|
| 107 |
-
"step": 700
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 3.0172413793103448,
|
| 111 |
-
"eval_loss": 2.549821138381958,
|
| 112 |
-
"eval_runtime": 9.2268,
|
| 113 |
-
"eval_samples_per_second": 12826.906,
|
| 114 |
-
"eval_steps_per_second": 6.286,
|
| 115 |
-
"step": 700
|
| 116 |
-
},
|
| 117 |
-
{
|
| 118 |
-
"epoch": 3.4482758620689653,
|
| 119 |
-
"grad_norm": 0.21819734573364258,
|
| 120 |
-
"learning_rate": 0.0019955491566955234,
|
| 121 |
-
"loss": 2.2858,
|
| 122 |
-
"step": 800
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 3.4482758620689653,
|
| 126 |
-
"eval_loss": 2.543490171432495,
|
| 127 |
-
"eval_runtime": 9.2266,
|
| 128 |
-
"eval_samples_per_second": 12827.175,
|
| 129 |
-
"eval_steps_per_second": 6.286,
|
| 130 |
-
"step": 800
|
| 131 |
-
},
|
| 132 |
-
{
|
| 133 |
-
"epoch": 3.8793103448275863,
|
| 134 |
-
"grad_norm": 0.16630978882312775,
|
| 135 |
-
"learning_rate": 0.0019941754182303075,
|
| 136 |
-
"loss": 2.3272,
|
| 137 |
-
"step": 900
|
| 138 |
-
},
|
| 139 |
-
{
|
| 140 |
-
"epoch": 3.8793103448275863,
|
| 141 |
-
"eval_loss": 2.5223655700683594,
|
| 142 |
-
"eval_runtime": 9.4402,
|
| 143 |
-
"eval_samples_per_second": 12536.875,
|
| 144 |
-
"eval_steps_per_second": 6.144,
|
| 145 |
-
"step": 900
|
| 146 |
-
},
|
| 147 |
-
{
|
| 148 |
-
"epoch": 4.310344827586207,
|
| 149 |
-
"grad_norm": 0.18484139442443848,
|
| 150 |
-
"learning_rate": 0.0019926178007739293,
|
| 151 |
-
"loss": 2.2288,
|
| 152 |
-
"step": 1000
|
| 153 |
-
},
|
| 154 |
-
{
|
| 155 |
-
"epoch": 4.310344827586207,
|
| 156 |
-
"eval_loss": 2.5807507038116455,
|
| 157 |
-
"eval_runtime": 9.3252,
|
| 158 |
-
"eval_samples_per_second": 12691.536,
|
| 159 |
-
"eval_steps_per_second": 6.22,
|
| 160 |
-
"step": 1000
|
| 161 |
-
},
|
| 162 |
-
{
|
| 163 |
-
"epoch": 4.741379310344827,
|
| 164 |
-
"grad_norm": 0.19197525084018707,
|
| 165 |
-
"learning_rate": 0.0019908765924175256,
|
| 166 |
-
"loss": 2.2444,
|
| 167 |
-
"step": 1100
|
| 168 |
-
},
|
| 169 |
-
{
|
| 170 |
-
"epoch": 4.741379310344827,
|
| 171 |
-
"eval_loss": 2.553419589996338,
|
| 172 |
-
"eval_runtime": 9.2519,
|
| 173 |
-
"eval_samples_per_second": 12792.034,
|
| 174 |
-
"eval_steps_per_second": 6.269,
|
| 175 |
-
"step": 1100
|
| 176 |
-
},
|
| 177 |
-
{
|
| 178 |
-
"epoch": 5.172413793103448,
|
| 179 |
-
"grad_norm": 0.21536719799041748,
|
| 180 |
-
"learning_rate": 0.001988952115208524,
|
| 181 |
-
"loss": 2.1968,
|
| 182 |
-
"step": 1200
|
| 183 |
-
},
|
| 184 |
-
{
|
| 185 |
-
"epoch": 5.172413793103448,
|
| 186 |
-
"eval_loss": 2.6241047382354736,
|
| 187 |
-
"eval_runtime": 9.2642,
|
| 188 |
-
"eval_samples_per_second": 12775.054,
|
| 189 |
-
"eval_steps_per_second": 6.261,
|
| 190 |
-
"step": 1200
|
| 191 |
-
},
|
| 192 |
-
{
|
| 193 |
-
"epoch": 5.603448275862069,
|
| 194 |
-
"grad_norm": 0.19505859911441803,
|
| 195 |
-
"learning_rate": 0.001986844725091078,
|
| 196 |
-
"loss": 2.1572,
|
| 197 |
-
"step": 1300
|
| 198 |
-
},
|
| 199 |
-
{
|
| 200 |
-
"epoch": 5.603448275862069,
|
| 201 |
-
"eval_loss": 2.598952531814575,
|
| 202 |
-
"eval_runtime": 9.2767,
|
| 203 |
-
"eval_samples_per_second": 12757.901,
|
| 204 |
-
"eval_steps_per_second": 6.252,
|
| 205 |
-
"step": 1300
|
| 206 |
-
},
|
| 207 |
-
{
|
| 208 |
-
"epoch": 6.0344827586206895,
|
| 209 |
-
"grad_norm": 0.23920711874961853,
|
| 210 |
-
"learning_rate": 0.0019845548118402334,
|
| 211 |
-
"loss": 2.1771,
|
| 212 |
-
"step": 1400
|
| 213 |
-
},
|
| 214 |
-
{
|
| 215 |
-
"epoch": 6.0344827586206895,
|
| 216 |
-
"eval_loss": 2.670865535736084,
|
| 217 |
-
"eval_runtime": 9.4662,
|
| 218 |
-
"eval_samples_per_second": 12502.495,
|
| 219 |
-
"eval_steps_per_second": 6.127,
|
| 220 |
-
"step": 1400
|
| 221 |
-
},
|
| 222 |
-
{
|
| 223 |
-
"epoch": 6.4655172413793105,
|
| 224 |
-
"grad_norm": 0.18848589062690735,
|
| 225 |
-
"learning_rate": 0.0019820827989898353,
|
| 226 |
-
"loss": 2.0576,
|
| 227 |
-
"step": 1500
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 6.4655172413793105,
|
| 231 |
-
"eval_loss": 2.640592575073242,
|
| 232 |
-
"eval_runtime": 9.3904,
|
| 233 |
-
"eval_samples_per_second": 12603.362,
|
| 234 |
-
"eval_steps_per_second": 6.177,
|
| 235 |
-
"step": 1500
|
| 236 |
-
},
|
| 237 |
-
{
|
| 238 |
-
"epoch": 6.896551724137931,
|
| 239 |
-
"grad_norm": 0.18979904055595398,
|
| 240 |
-
"learning_rate": 0.0019794291437541956,
|
| 241 |
-
"loss": 2.1191,
|
| 242 |
-
"step": 1600
|
| 243 |
-
},
|
| 244 |
-
{
|
| 245 |
-
"epoch": 6.896551724137931,
|
| 246 |
-
"eval_loss": 2.6196117401123047,
|
| 247 |
-
"eval_runtime": 9.2558,
|
| 248 |
-
"eval_samples_per_second": 12786.7,
|
| 249 |
-
"eval_steps_per_second": 6.266,
|
| 250 |
-
"step": 1600
|
| 251 |
-
},
|
| 252 |
-
{
|
| 253 |
-
"epoch": 7.327586206896552,
|
| 254 |
-
"grad_norm": 0.24726751446723938,
|
| 255 |
-
"learning_rate": 0.001976594336943526,
|
| 256 |
-
"loss": 2.0069,
|
| 257 |
-
"step": 1700
|
| 258 |
-
},
|
| 259 |
-
{
|
| 260 |
-
"epoch": 7.327586206896552,
|
| 261 |
-
"eval_loss": 2.7223079204559326,
|
| 262 |
-
"eval_runtime": 9.3003,
|
| 263 |
-
"eval_samples_per_second": 12725.505,
|
| 264 |
-
"eval_steps_per_second": 6.236,
|
| 265 |
-
"step": 1700
|
| 266 |
-
},
|
| 267 |
-
{
|
| 268 |
-
"epoch": 7.758620689655173,
|
| 269 |
-
"grad_norm": 0.21912235021591187,
|
| 270 |
-
"learning_rate": 0.0019735789028731605,
|
| 271 |
-
"loss": 2.0379,
|
| 272 |
-
"step": 1800
|
| 273 |
-
},
|
| 274 |
-
{
|
| 275 |
-
"epoch": 7.758620689655173,
|
| 276 |
-
"eval_loss": 2.6878578662872314,
|
| 277 |
-
"eval_runtime": 9.3885,
|
| 278 |
-
"eval_samples_per_second": 12605.897,
|
| 279 |
-
"eval_steps_per_second": 6.178,
|
| 280 |
-
"step": 1800
|
| 281 |
-
},
|
| 282 |
-
{
|
| 283 |
-
"epoch": 8.189655172413794,
|
| 284 |
-
"grad_norm": 0.22405335307121277,
|
| 285 |
-
"learning_rate": 0.0019703833992665795,
|
| 286 |
-
"loss": 1.9835,
|
| 287 |
-
"step": 1900
|
| 288 |
-
},
|
| 289 |
-
{
|
| 290 |
-
"epoch": 8.189655172413794,
|
| 291 |
-
"eval_loss": 2.8071248531341553,
|
| 292 |
-
"eval_runtime": 9.2669,
|
| 293 |
-
"eval_samples_per_second": 12771.428,
|
| 294 |
-
"eval_steps_per_second": 6.259,
|
| 295 |
-
"step": 1900
|
| 296 |
-
},
|
| 297 |
-
{
|
| 298 |
-
"epoch": 8.620689655172415,
|
| 299 |
-
"grad_norm": 0.2046048790216446,
|
| 300 |
-
"learning_rate": 0.0019670084171522564,
|
| 301 |
-
"loss": 1.9511,
|
| 302 |
-
"step": 2000
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 8.620689655172415,
|
| 306 |
-
"eval_loss": 2.7486164569854736,
|
| 307 |
-
"eval_runtime": 9.4519,
|
| 308 |
-
"eval_samples_per_second": 12521.34,
|
| 309 |
-
"eval_steps_per_second": 6.136,
|
| 310 |
-
"step": 2000
|
| 311 |
-
},
|
| 312 |
-
{
|
| 313 |
-
"epoch": 9.051724137931034,
|
| 314 |
-
"grad_norm": 0.25268155336380005,
|
| 315 |
-
"learning_rate": 0.0019634545807543425,
|
| 316 |
-
"loss": 1.9748,
|
| 317 |
-
"step": 2100
|
| 318 |
-
},
|
| 319 |
-
{
|
| 320 |
-
"epoch": 9.051724137931034,
|
| 321 |
-
"eval_loss": 2.8860645294189453,
|
| 322 |
-
"eval_runtime": 9.397,
|
| 323 |
-
"eval_samples_per_second": 12594.608,
|
| 324 |
-
"eval_steps_per_second": 6.172,
|
| 325 |
-
"step": 2100
|
| 326 |
-
},
|
| 327 |
-
{
|
| 328 |
-
"epoch": 9.482758620689655,
|
| 329 |
-
"grad_norm": 0.21367767453193665,
|
| 330 |
-
"learning_rate": 0.0019597225473772122,
|
| 331 |
-
"loss": 1.8546,
|
| 332 |
-
"step": 2200
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 9.482758620689655,
|
| 336 |
-
"eval_loss": 2.8317956924438477,
|
| 337 |
-
"eval_runtime": 9.3796,
|
| 338 |
-
"eval_samples_per_second": 12617.898,
|
| 339 |
-
"eval_steps_per_second": 6.184,
|
| 340 |
-
"step": 2200
|
| 341 |
-
},
|
| 342 |
-
{
|
| 343 |
-
"epoch": 9.913793103448276,
|
| 344 |
-
"grad_norm": 0.20437228679656982,
|
| 345 |
-
"learning_rate": 0.001955813007283891,
|
| 346 |
-
"loss": 1.9269,
|
| 347 |
-
"step": 2300
|
| 348 |
-
},
|
| 349 |
-
{
|
| 350 |
-
"epoch": 9.913793103448276,
|
| 351 |
-
"eval_loss": 2.774157762527466,
|
| 352 |
-
"eval_runtime": 9.4231,
|
| 353 |
-
"eval_samples_per_second": 12559.694,
|
| 354 |
-
"eval_steps_per_second": 6.155,
|
| 355 |
-
"step": 2300
|
| 356 |
-
},
|
| 357 |
-
{
|
| 358 |
-
"epoch": 10.344827586206897,
|
| 359 |
-
"grad_norm": 0.23834232985973358,
|
| 360 |
-
"learning_rate": 0.001951726683568388,
|
| 361 |
-
"loss": 1.8023,
|
| 362 |
-
"step": 2400
|
| 363 |
-
},
|
| 364 |
-
{
|
| 365 |
-
"epoch": 10.344827586206897,
|
| 366 |
-
"eval_loss": 2.9143717288970947,
|
| 367 |
-
"eval_runtime": 9.2647,
|
| 368 |
-
"eval_samples_per_second": 12774.461,
|
| 369 |
-
"eval_steps_per_second": 6.26,
|
| 370 |
-
"step": 2400
|
| 371 |
-
},
|
| 372 |
-
{
|
| 373 |
-
"epoch": 10.775862068965518,
|
| 374 |
-
"grad_norm": 0.24124032258987427,
|
| 375 |
-
"learning_rate": 0.0019474643320219532,
|
| 376 |
-
"loss": 1.8488,
|
| 377 |
-
"step": 2500
|
| 378 |
-
},
|
| 379 |
-
{
|
| 380 |
-
"epoch": 10.775862068965518,
|
| 381 |
-
"eval_loss": 2.8489134311676025,
|
| 382 |
-
"eval_runtime": 9.438,
|
| 383 |
-
"eval_samples_per_second": 12539.884,
|
| 384 |
-
"eval_steps_per_second": 6.145,
|
| 385 |
-
"step": 2500
|
| 386 |
-
},
|
| 387 |
-
{
|
| 388 |
-
"epoch": 11.206896551724139,
|
| 389 |
-
"grad_norm": 0.2650582194328308,
|
| 390 |
-
"learning_rate": 0.00194302674099329,
|
| 391 |
-
"loss": 1.7888,
|
| 392 |
-
"step": 2600
|
| 393 |
-
},
|
| 394 |
-
{
|
| 395 |
-
"epoch": 11.206896551724139,
|
| 396 |
-
"eval_loss": 2.997723340988159,
|
| 397 |
-
"eval_runtime": 9.2695,
|
| 398 |
-
"eval_samples_per_second": 12767.769,
|
| 399 |
-
"eval_steps_per_second": 6.257,
|
| 400 |
-
"step": 2600
|
| 401 |
-
},
|
| 402 |
-
{
|
| 403 |
-
"epoch": 11.637931034482758,
|
| 404 |
-
"grad_norm": 0.23494461178779602,
|
| 405 |
-
"learning_rate": 0.0019384147312427463,
|
| 406 |
-
"loss": 1.7675,
|
| 407 |
-
"step": 2700
|
| 408 |
-
},
|
| 409 |
-
{
|
| 410 |
-
"epoch": 11.637931034482758,
|
| 411 |
-
"eval_loss": 2.9378740787506104,
|
| 412 |
-
"eval_runtime": 9.4233,
|
| 413 |
-
"eval_samples_per_second": 12559.421,
|
| 414 |
-
"eval_steps_per_second": 6.155,
|
| 415 |
-
"step": 2700
|
| 416 |
-
},
|
| 417 |
-
{
|
| 418 |
-
"epoch": 12.068965517241379,
|
| 419 |
-
"grad_norm": 0.28737518191337585,
|
| 420 |
-
"learning_rate": 0.001933629155790508,
|
| 421 |
-
"loss": 1.7851,
|
| 422 |
-
"step": 2800
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 12.068965517241379,
|
| 426 |
-
"eval_loss": 3.1028385162353516,
|
| 427 |
-
"eval_runtime": 9.2265,
|
| 428 |
-
"eval_samples_per_second": 12827.292,
|
| 429 |
-
"eval_steps_per_second": 6.286,
|
| 430 |
-
"step": 2800
|
| 431 |
-
},
|
| 432 |
-
{
|
| 433 |
-
"epoch": 12.5,
|
| 434 |
-
"grad_norm": 0.2447143793106079,
|
| 435 |
-
"learning_rate": 0.0019286708997588277,
|
| 436 |
-
"loss": 1.6799,
|
| 437 |
-
"step": 2900
|
| 438 |
-
},
|
| 439 |
-
{
|
| 440 |
-
"epoch": 12.5,
|
| 441 |
-
"eval_loss": 3.0367963314056396,
|
| 442 |
-
"eval_runtime": 9.4036,
|
| 443 |
-
"eval_samples_per_second": 12585.728,
|
| 444 |
-
"eval_steps_per_second": 6.168,
|
| 445 |
-
"step": 2900
|
| 446 |
-
},
|
| 447 |
-
{
|
| 448 |
-
"epoch": 12.931034482758621,
|
| 449 |
-
"grad_norm": 0.23348909616470337,
|
| 450 |
-
"learning_rate": 0.0019235408802083177,
|
| 451 |
-
"loss": 1.7546,
|
| 452 |
-
"step": 3000
|
| 453 |
-
},
|
| 454 |
-
{
|
| 455 |
-
"epoch": 12.931034482758621,
|
| 456 |
-
"eval_loss": 2.9751391410827637,
|
| 457 |
-
"eval_runtime": 9.3086,
|
| 458 |
-
"eval_samples_per_second": 12714.109,
|
| 459 |
-
"eval_steps_per_second": 6.231,
|
| 460 |
-
"step": 3000
|
| 461 |
-
},
|
| 462 |
-
{
|
| 463 |
-
"epoch": 13.362068965517242,
|
| 464 |
-
"grad_norm": 0.23927970230579376,
|
| 465 |
-
"learning_rate": 0.0019182400459683319,
|
| 466 |
-
"loss": 1.6305,
|
| 467 |
-
"step": 3100
|
| 468 |
-
},
|
| 469 |
-
{
|
| 470 |
-
"epoch": 13.362068965517242,
|
| 471 |
-
"eval_loss": 3.11104679107666,
|
| 472 |
-
"eval_runtime": 9.2164,
|
| 473 |
-
"eval_samples_per_second": 12841.37,
|
| 474 |
-
"eval_steps_per_second": 6.293,
|
| 475 |
-
"step": 3100
|
| 476 |
-
},
|
| 477 |
-
{
|
| 478 |
-
"epoch": 13.793103448275861,
|
| 479 |
-
"grad_norm": 0.2492324709892273,
|
| 480 |
-
"learning_rate": 0.0019127693774614737,
|
| 481 |
-
"loss": 1.6843,
|
| 482 |
-
"step": 3200
|
| 483 |
-
},
|
| 484 |
-
{
|
| 485 |
-
"epoch": 13.793103448275861,
|
| 486 |
-
"eval_loss": 3.0621368885040283,
|
| 487 |
-
"eval_runtime": 9.6341,
|
| 488 |
-
"eval_samples_per_second": 12284.569,
|
| 489 |
-
"eval_steps_per_second": 6.02,
|
| 490 |
-
"step": 3200
|
| 491 |
-
},
|
| 492 |
-
{
|
| 493 |
-
"epoch": 14.224137931034482,
|
| 494 |
-
"grad_norm": 0.2568209171295166,
|
| 495 |
-
"learning_rate": 0.0019071298865222619,
|
| 496 |
-
"loss": 1.6259,
|
| 497 |
-
"step": 3300
|
| 498 |
-
},
|
| 499 |
-
{
|
| 500 |
-
"epoch": 14.224137931034482,
|
| 501 |
-
"eval_loss": 3.23667311668396,
|
| 502 |
-
"eval_runtime": 9.3875,
|
| 503 |
-
"eval_samples_per_second": 12607.29,
|
| 504 |
-
"eval_steps_per_second": 6.178,
|
| 505 |
-
"step": 3300
|
| 506 |
-
},
|
| 507 |
-
{
|
| 508 |
-
"epoch": 14.655172413793103,
|
| 509 |
-
"grad_norm": 0.2605755627155304,
|
| 510 |
-
"learning_rate": 0.0019013226162099856,
|
| 511 |
-
"loss": 1.6142,
|
| 512 |
-
"step": 3400
|
| 513 |
-
},
|
| 514 |
-
{
|
| 515 |
-
"epoch": 14.655172413793103,
|
| 516 |
-
"eval_loss": 3.167109489440918,
|
| 517 |
-
"eval_runtime": 9.2685,
|
| 518 |
-
"eval_samples_per_second": 12769.199,
|
| 519 |
-
"eval_steps_per_second": 6.258,
|
| 520 |
-
"step": 3400
|
| 521 |
-
},
|
| 522 |
-
{
|
| 523 |
-
"epoch": 15.086206896551724,
|
| 524 |
-
"grad_norm": 0.23708142340183258,
|
| 525 |
-
"learning_rate": 0.001895348640615783,
|
| 526 |
-
"loss": 1.6297,
|
| 527 |
-
"step": 3500
|
| 528 |
-
},
|
| 529 |
-
{
|
| 530 |
-
"epoch": 15.086206896551724,
|
| 531 |
-
"eval_loss": 3.3472063541412354,
|
| 532 |
-
"eval_runtime": 9.2633,
|
| 533 |
-
"eval_samples_per_second": 12776.346,
|
| 534 |
-
"eval_steps_per_second": 6.261,
|
| 535 |
-
"step": 3500
|
| 536 |
-
},
|
| 537 |
-
{
|
| 538 |
-
"epoch": 15.517241379310345,
|
| 539 |
-
"grad_norm": 0.26707184314727783,
|
| 540 |
-
"learning_rate": 0.0018892090646639814,
|
| 541 |
-
"loss": 1.5412,
|
| 542 |
-
"step": 3600
|
| 543 |
-
},
|
| 544 |
-
{
|
| 545 |
-
"epoch": 15.517241379310345,
|
| 546 |
-
"eval_loss": 3.2221648693084717,
|
| 547 |
-
"eval_runtime": 9.3835,
|
| 548 |
-
"eval_samples_per_second": 12612.691,
|
| 549 |
-
"eval_steps_per_second": 6.181,
|
| 550 |
-
"step": 3600
|
| 551 |
-
},
|
| 552 |
-
{
|
| 553 |
-
"epoch": 15.948275862068966,
|
| 554 |
-
"grad_norm": 0.281376451253891,
|
| 555 |
-
"learning_rate": 0.001882905023907735,
|
| 556 |
-
"loss": 1.612,
|
| 557 |
-
"step": 3700
|
| 558 |
-
},
|
| 559 |
-
{
|
| 560 |
-
"epoch": 15.948275862068966,
|
| 561 |
-
"eval_loss": 3.1913859844207764,
|
| 562 |
-
"eval_runtime": 9.2915,
|
| 563 |
-
"eval_samples_per_second": 12737.598,
|
| 564 |
-
"eval_steps_per_second": 6.242,
|
| 565 |
-
"step": 3700
|
| 566 |
-
},
|
| 567 |
-
{
|
| 568 |
-
"epoch": 16.379310344827587,
|
| 569 |
-
"grad_norm": 0.3034946322441101,
|
| 570 |
-
"learning_rate": 0.0018764376843189978,
|
| 571 |
-
"loss": 1.4939,
|
| 572 |
-
"step": 3800
|
| 573 |
-
},
|
| 574 |
-
{
|
| 575 |
-
"epoch": 16.379310344827587,
|
| 576 |
-
"eval_loss": 3.3291513919830322,
|
| 577 |
-
"eval_runtime": 9.3993,
|
| 578 |
-
"eval_samples_per_second": 12591.436,
|
| 579 |
-
"eval_steps_per_second": 6.171,
|
| 580 |
-
"step": 3800
|
| 581 |
-
},
|
| 582 |
-
{
|
| 583 |
-
"epoch": 16.810344827586206,
|
| 584 |
-
"grad_norm": 0.2752383053302765,
|
| 585 |
-
"learning_rate": 0.0018698082420728684,
|
| 586 |
-
"loss": 1.5533,
|
| 587 |
-
"step": 3900
|
| 588 |
-
},
|
| 589 |
-
{
|
| 590 |
-
"epoch": 16.810344827586206,
|
| 591 |
-
"eval_loss": 3.2778160572052,
|
| 592 |
-
"eval_runtime": 9.2577,
|
| 593 |
-
"eval_samples_per_second": 12784.003,
|
| 594 |
-
"eval_steps_per_second": 6.265,
|
| 595 |
-
"step": 3900
|
| 596 |
-
},
|
| 597 |
-
{
|
| 598 |
-
"epoch": 17.24137931034483,
|
| 599 |
-
"grad_norm": 0.24308009445667267,
|
| 600 |
-
"learning_rate": 0.0018630179233263503,
|
| 601 |
-
"loss": 1.4946,
|
| 602 |
-
"step": 4000
|
| 603 |
-
},
|
| 604 |
-
{
|
| 605 |
-
"epoch": 17.24137931034483,
|
| 606 |
-
"eval_loss": 3.4539055824279785,
|
| 607 |
-
"eval_runtime": 9.2861,
|
| 608 |
-
"eval_samples_per_second": 12744.951,
|
| 609 |
-
"eval_steps_per_second": 6.246,
|
| 610 |
-
"step": 4000
|
| 611 |
-
},
|
| 612 |
-
{
|
| 613 |
-
"epoch": 17.67241379310345,
|
| 614 |
-
"grad_norm": 0.27771443128585815,
|
| 615 |
-
"learning_rate": 0.0018560679839915678,
|
| 616 |
-
"loss": 1.4915,
|
| 617 |
-
"step": 4100
|
| 618 |
-
},
|
| 619 |
-
{
|
| 620 |
-
"epoch": 17.67241379310345,
|
| 621 |
-
"eval_loss": 3.3372902870178223,
|
| 622 |
-
"eval_runtime": 9.3808,
|
| 623 |
-
"eval_samples_per_second": 12616.313,
|
| 624 |
-
"eval_steps_per_second": 6.183,
|
| 625 |
-
"step": 4100
|
| 626 |
-
},
|
| 627 |
-
{
|
| 628 |
-
"epoch": 18.103448275862068,
|
| 629 |
-
"grad_norm": 0.23893053829669952,
|
| 630 |
-
"learning_rate": 0.0018489597095034747,
|
| 631 |
-
"loss": 1.502,
|
| 632 |
-
"step": 4200
|
| 633 |
-
},
|
| 634 |
-
{
|
| 635 |
-
"epoch": 18.103448275862068,
|
| 636 |
-
"eval_loss": 3.5338973999023438,
|
| 637 |
-
"eval_runtime": 9.3911,
|
| 638 |
-
"eval_samples_per_second": 12602.423,
|
| 639 |
-
"eval_steps_per_second": 6.176,
|
| 640 |
-
"step": 4200
|
| 641 |
-
},
|
| 642 |
-
{
|
| 643 |
-
"epoch": 18.53448275862069,
|
| 644 |
-
"grad_norm": 0.27007514238357544,
|
| 645 |
-
"learning_rate": 0.0018416944145821076,
|
| 646 |
-
"loss": 1.4326,
|
| 647 |
-
"step": 4300
|
| 648 |
-
},
|
| 649 |
-
{
|
| 650 |
-
"epoch": 18.53448275862069,
|
| 651 |
-
"eval_loss": 3.4548091888427734,
|
| 652 |
-
"eval_runtime": 9.4336,
|
| 653 |
-
"eval_samples_per_second": 12545.738,
|
| 654 |
-
"eval_steps_per_second": 6.148,
|
| 655 |
-
"step": 4300
|
| 656 |
-
},
|
| 657 |
-
{
|
| 658 |
-
"epoch": 18.96551724137931,
|
| 659 |
-
"grad_norm": 0.2778242528438568,
|
| 660 |
-
"learning_rate": 0.0018342734429894186,
|
| 661 |
-
"loss": 1.4974,
|
| 662 |
-
"step": 4400
|
| 663 |
-
},
|
| 664 |
-
{
|
| 665 |
-
"epoch": 18.96551724137931,
|
| 666 |
-
"eval_loss": 3.3584742546081543,
|
| 667 |
-
"eval_runtime": 9.3945,
|
| 668 |
-
"eval_samples_per_second": 12597.905,
|
| 669 |
-
"eval_steps_per_second": 6.174,
|
| 670 |
-
"step": 4400
|
| 671 |
-
},
|
| 672 |
-
{
|
| 673 |
-
"epoch": 19.396551724137932,
|
| 674 |
-
"grad_norm": 0.2755739390850067,
|
| 675 |
-
"learning_rate": 0.0018266981672807382,
|
| 676 |
-
"loss": 1.3891,
|
| 677 |
-
"step": 4500
|
| 678 |
-
},
|
| 679 |
-
{
|
| 680 |
-
"epoch": 19.396551724137932,
|
| 681 |
-
"eval_loss": 3.53035831451416,
|
| 682 |
-
"eval_runtime": 9.3977,
|
| 683 |
-
"eval_samples_per_second": 12593.626,
|
| 684 |
-
"eval_steps_per_second": 6.172,
|
| 685 |
-
"step": 4500
|
| 686 |
-
},
|
| 687 |
-
{
|
| 688 |
-
"epoch": 19.82758620689655,
|
| 689 |
-
"grad_norm": 0.2956218719482422,
|
| 690 |
-
"learning_rate": 0.0018189699885509127,
|
| 691 |
-
"loss": 1.4471,
|
| 692 |
-
"step": 4600
|
| 693 |
-
},
|
| 694 |
-
{
|
| 695 |
-
"epoch": 19.82758620689655,
|
| 696 |
-
"eval_loss": 3.429187536239624,
|
| 697 |
-
"eval_runtime": 9.3785,
|
| 698 |
-
"eval_samples_per_second": 12619.367,
|
| 699 |
-
"eval_steps_per_second": 6.184,
|
| 700 |
-
"step": 4600
|
| 701 |
-
},
|
| 702 |
-
{
|
| 703 |
-
"epoch": 20.25862068965517,
|
| 704 |
-
"grad_norm": 0.26031580567359924,
|
| 705 |
-
"learning_rate": 0.0018110903361751639,
|
| 706 |
-
"loss": 1.3933,
|
| 707 |
-
"step": 4700
|
| 708 |
-
},
|
| 709 |
-
{
|
| 710 |
-
"epoch": 20.25862068965517,
|
| 711 |
-
"eval_loss": 3.6417198181152344,
|
| 712 |
-
"eval_runtime": 9.2276,
|
| 713 |
-
"eval_samples_per_second": 12825.78,
|
| 714 |
-
"eval_steps_per_second": 6.286,
|
| 715 |
-
"step": 4700
|
| 716 |
-
},
|
| 717 |
-
{
|
| 718 |
-
"epoch": 20.689655172413794,
|
| 719 |
-
"grad_norm": 0.29798653721809387,
|
| 720 |
-
"learning_rate": 0.0018030606675447152,
|
| 721 |
-
"loss": 1.3977,
|
| 722 |
-
"step": 4800
|
| 723 |
-
},
|
| 724 |
-
{
|
| 725 |
-
"epoch": 20.689655172413794,
|
| 726 |
-
"eval_loss": 3.537259817123413,
|
| 727 |
-
"eval_runtime": 9.3854,
|
| 728 |
-
"eval_samples_per_second": 12610.18,
|
| 729 |
-
"eval_steps_per_second": 6.18,
|
| 730 |
-
"step": 4800
|
| 731 |
-
},
|
| 732 |
-
{
|
| 733 |
-
"epoch": 21.120689655172413,
|
| 734 |
-
"grad_norm": 0.2423907071352005,
|
| 735 |
-
"learning_rate": 0.0017948824677972398,
|
| 736 |
-
"loss": 1.4009,
|
| 737 |
-
"step": 4900
|
| 738 |
-
},
|
| 739 |
-
{
|
| 740 |
-
"epoch": 21.120689655172413,
|
| 741 |
-
"eval_loss": 3.746032476425171,
|
| 742 |
-
"eval_runtime": 9.4268,
|
| 743 |
-
"eval_samples_per_second": 12554.68,
|
| 744 |
-
"eval_steps_per_second": 6.153,
|
| 745 |
-
"step": 4900
|
| 746 |
-
},
|
| 747 |
-
{
|
| 748 |
-
"epoch": 21.551724137931036,
|
| 749 |
-
"grad_norm": 0.285411536693573,
|
| 750 |
-
"learning_rate": 0.0017865572495421743,
|
| 751 |
-
"loss": 1.3483,
|
| 752 |
-
"step": 5000
|
| 753 |
-
},
|
| 754 |
-
{
|
| 755 |
-
"epoch": 21.551724137931036,
|
| 756 |
-
"eval_loss": 3.626232624053955,
|
| 757 |
-
"eval_runtime": 9.2375,
|
| 758 |
-
"eval_samples_per_second": 12812.033,
|
| 759 |
-
"eval_steps_per_second": 6.279,
|
| 760 |
-
"step": 5000
|
| 761 |
-
},
|
| 762 |
-
{
|
| 763 |
-
"epoch": 21.982758620689655,
|
| 764 |
-
"grad_norm": 0.2717497944831848,
|
| 765 |
-
"learning_rate": 0.0017780865525809514,
|
| 766 |
-
"loss": 1.4067,
|
| 767 |
-
"step": 5100
|
| 768 |
-
},
|
| 769 |
-
{
|
| 770 |
-
"epoch": 21.982758620689655,
|
| 771 |
-
"eval_loss": 3.52826189994812,
|
| 772 |
-
"eval_runtime": 9.3933,
|
| 773 |
-
"eval_samples_per_second": 12599.514,
|
| 774 |
-
"eval_steps_per_second": 6.175,
|
| 775 |
-
"step": 5100
|
| 776 |
-
},
|
| 777 |
-
{
|
| 778 |
-
"epoch": 22.413793103448278,
|
| 779 |
-
"grad_norm": 0.2960723042488098,
|
| 780 |
-
"learning_rate": 0.001769471943622206,
|
| 781 |
-
"loss": 1.3058,
|
| 782 |
-
"step": 5200
|
| 783 |
-
},
|
| 784 |
-
{
|
| 785 |
-
"epoch": 22.413793103448278,
|
| 786 |
-
"eval_loss": 3.7002322673797607,
|
| 787 |
-
"eval_runtime": 9.2501,
|
| 788 |
-
"eval_samples_per_second": 12794.575,
|
| 789 |
-
"eval_steps_per_second": 6.27,
|
| 790 |
-
"step": 5200
|
| 791 |
-
},
|
| 792 |
-
{
|
| 793 |
-
"epoch": 22.844827586206897,
|
| 794 |
-
"grad_norm": 0.2612112760543823,
|
| 795 |
-
"learning_rate": 0.001760715015992,
|
| 796 |
-
"loss": 1.3648,
|
| 797 |
-
"step": 5300
|
| 798 |
-
},
|
| 799 |
-
{
|
| 800 |
-
"epoch": 22.844827586206897,
|
| 801 |
-
"eval_loss": 3.6350343227386475,
|
| 802 |
-
"eval_runtime": 9.3548,
|
| 803 |
-
"eval_samples_per_second": 12651.31,
|
| 804 |
-
"eval_steps_per_second": 6.2,
|
| 805 |
-
"step": 5300
|
| 806 |
-
},
|
| 807 |
-
{
|
| 808 |
-
"epoch": 23.275862068965516,
|
| 809 |
-
"grad_norm": 0.2936803996562958,
|
| 810 |
-
"learning_rate": 0.0017518173893391294,
|
| 811 |
-
"loss": 1.3116,
|
| 812 |
-
"step": 5400
|
| 813 |
-
},
|
| 814 |
-
{
|
| 815 |
-
"epoch": 23.275862068965516,
|
| 816 |
-
"eval_loss": 3.8155357837677,
|
| 817 |
-
"eval_runtime": 9.3802,
|
| 818 |
-
"eval_samples_per_second": 12617.144,
|
| 819 |
-
"eval_steps_per_second": 6.183,
|
| 820 |
-
"step": 5400
|
| 821 |
-
},
|
| 822 |
-
{
|
| 823 |
-
"epoch": 23.70689655172414,
|
| 824 |
-
"grad_norm": 0.31589367985725403,
|
| 825 |
-
"learning_rate": 0.0017427807093355573,
|
| 826 |
-
"loss": 1.3237,
|
| 827 |
-
"step": 5500
|
| 828 |
-
},
|
| 829 |
-
{
|
| 830 |
-
"epoch": 23.70689655172414,
|
| 831 |
-
"eval_loss": 3.7021758556365967,
|
| 832 |
-
"eval_runtime": 9.2626,
|
| 833 |
-
"eval_samples_per_second": 12777.362,
|
| 834 |
-
"eval_steps_per_second": 6.262,
|
| 835 |
-
"step": 5500
|
| 836 |
-
},
|
| 837 |
-
{
|
| 838 |
-
"epoch": 24.137931034482758,
|
| 839 |
-
"grad_norm": 0.2593901753425598,
|
| 840 |
-
"learning_rate": 0.0017336066473720379,
|
| 841 |
-
"loss": 1.321,
|
| 842 |
-
"step": 5600
|
| 843 |
-
},
|
| 844 |
-
{
|
| 845 |
-
"epoch": 24.137931034482758,
|
| 846 |
-
"eval_loss": 3.911588191986084,
|
| 847 |
-
"eval_runtime": 9.3553,
|
| 848 |
-
"eval_samples_per_second": 12650.682,
|
| 849 |
-
"eval_steps_per_second": 6.2,
|
| 850 |
-
"step": 5600
|
| 851 |
-
},
|
| 852 |
-
{
|
| 853 |
-
"epoch": 24.56896551724138,
|
| 854 |
-
"grad_norm": 0.25670963525772095,
|
| 855 |
-
"learning_rate": 0.0017242969002489832,
|
| 856 |
-
"loss": 1.2831,
|
| 857 |
-
"step": 5700
|
| 858 |
-
},
|
| 859 |
-
{
|
| 860 |
-
"epoch": 24.56896551724138,
|
| 861 |
-
"eval_loss": 3.7876436710357666,
|
| 862 |
-
"eval_runtime": 9.2098,
|
| 863 |
-
"eval_samples_per_second": 12850.53,
|
| 864 |
-
"eval_steps_per_second": 6.298,
|
| 865 |
-
"step": 5700
|
| 866 |
-
},
|
| 867 |
-
{
|
| 868 |
-
"epoch": 25.0,
|
| 869 |
-
"grad_norm": 0.2661011815071106,
|
| 870 |
-
"learning_rate": 0.0017148531898626277,
|
| 871 |
-
"loss": 1.3339,
|
| 872 |
-
"step": 5800
|
| 873 |
-
},
|
| 874 |
-
{
|
| 875 |
-
"epoch": 25.0,
|
| 876 |
-
"eval_loss": 3.7584354877471924,
|
| 877 |
-
"eval_runtime": 9.3748,
|
| 878 |
-
"eval_samples_per_second": 12624.378,
|
| 879 |
-
"eval_steps_per_second": 6.187,
|
| 880 |
-
"step": 5800
|
| 881 |
-
},
|
| 882 |
-
{
|
| 883 |
-
"epoch": 25.43103448275862,
|
| 884 |
-
"grad_norm": 0.28436627984046936,
|
| 885 |
-
"learning_rate": 0.0017052772628865526,
|
| 886 |
-
"loss": 1.2398,
|
| 887 |
-
"step": 5900
|
| 888 |
-
},
|
| 889 |
-
{
|
| 890 |
-
"epoch": 25.43103448275862,
|
| 891 |
-
"eval_loss": 3.871803045272827,
|
| 892 |
-
"eval_runtime": 9.2847,
|
| 893 |
-
"eval_samples_per_second": 12746.93,
|
| 894 |
-
"eval_steps_per_second": 6.247,
|
| 895 |
-
"step": 5900
|
| 896 |
-
},
|
| 897 |
-
{
|
| 898 |
-
"epoch": 25.862068965517242,
|
| 899 |
-
"grad_norm": 0.29255756735801697,
|
| 900 |
-
"learning_rate": 0.0016955708904486295,
|
| 901 |
-
"loss": 1.2999,
|
| 902 |
-
"step": 6000
|
| 903 |
-
},
|
| 904 |
-
{
|
| 905 |
-
"epoch": 25.862068965517242,
|
| 906 |
-
"eval_loss": 3.7788214683532715,
|
| 907 |
-
"eval_runtime": 9.402,
|
| 908 |
-
"eval_samples_per_second": 12587.813,
|
| 909 |
-
"eval_steps_per_second": 6.169,
|
| 910 |
-
"step": 6000
|
| 911 |
-
},
|
| 912 |
-
{
|
| 913 |
-
"epoch": 26.29310344827586,
|
| 914 |
-
"grad_norm": 0.2579859793186188,
|
| 915 |
-
"learning_rate": 0.0016857358678034368,
|
| 916 |
-
"loss": 1.2468,
|
| 917 |
-
"step": 6100
|
| 918 |
-
},
|
| 919 |
-
{
|
| 920 |
-
"epoch": 26.29310344827586,
|
| 921 |
-
"eval_loss": 3.988563060760498,
|
| 922 |
-
"eval_runtime": 9.3885,
|
| 923 |
-
"eval_samples_per_second": 12605.909,
|
| 924 |
-
"eval_steps_per_second": 6.178,
|
| 925 |
-
"step": 6100
|
| 926 |
-
},
|
| 927 |
-
{
|
| 928 |
-
"epoch": 26.724137931034484,
|
| 929 |
-
"grad_norm": 0.2829207479953766,
|
| 930 |
-
"learning_rate": 0.0016757740140002178,
|
| 931 |
-
"loss": 1.2634,
|
| 932 |
-
"step": 6200
|
| 933 |
-
},
|
| 934 |
-
{
|
| 935 |
-
"epoch": 26.724137931034484,
|
| 936 |
-
"eval_loss": 3.8294568061828613,
|
| 937 |
-
"eval_runtime": 9.2608,
|
| 938 |
-
"eval_samples_per_second": 12779.842,
|
| 939 |
-
"eval_steps_per_second": 6.263,
|
| 940 |
-
"step": 6200
|
| 941 |
-
},
|
| 942 |
-
{
|
| 943 |
-
"epoch": 27.155172413793103,
|
| 944 |
-
"grad_norm": 0.26081788539886475,
|
| 945 |
-
"learning_rate": 0.0016656871715464352,
|
| 946 |
-
"loss": 1.2572,
|
| 947 |
-
"step": 6300
|
| 948 |
-
},
|
| 949 |
-
{
|
| 950 |
-
"epoch": 27.155172413793103,
|
| 951 |
-
"eval_loss": 4.046365737915039,
|
| 952 |
-
"eval_runtime": 9.3759,
|
| 953 |
-
"eval_samples_per_second": 12622.851,
|
| 954 |
-
"eval_steps_per_second": 6.186,
|
| 955 |
-
"step": 6300
|
| 956 |
-
},
|
| 957 |
-
{
|
| 958 |
-
"epoch": 27.586206896551722,
|
| 959 |
-
"grad_norm": 0.27960658073425293,
|
| 960 |
-
"learning_rate": 0.001655477206066988,
|
| 961 |
-
"loss": 1.2288,
|
| 962 |
-
"step": 6400
|
| 963 |
-
},
|
| 964 |
-
{
|
| 965 |
-
"epoch": 27.586206896551722,
|
| 966 |
-
"eval_loss": 3.938596248626709,
|
| 967 |
-
"eval_runtime": 9.2164,
|
| 968 |
-
"eval_samples_per_second": 12841.411,
|
| 969 |
-
"eval_steps_per_second": 6.293,
|
| 970 |
-
"step": 6400
|
| 971 |
-
},
|
| 972 |
-
{
|
| 973 |
-
"epoch": 28.017241379310345,
|
| 974 |
-
"grad_norm": 0.283263236284256,
|
| 975 |
-
"learning_rate": 0.0016451460059591532,
|
| 976 |
-
"loss": 1.2708,
|
| 977 |
-
"step": 6500
|
| 978 |
-
},
|
| 979 |
-
{
|
| 980 |
-
"epoch": 28.017241379310345,
|
| 981 |
-
"eval_loss": 4.127839088439941,
|
| 982 |
-
"eval_runtime": 9.2469,
|
| 983 |
-
"eval_samples_per_second": 12799.012,
|
| 984 |
-
"eval_steps_per_second": 6.272,
|
| 985 |
-
"step": 6500
|
| 986 |
-
},
|
| 987 |
-
{
|
| 988 |
-
"epoch": 28.448275862068964,
|
| 989 |
-
"grad_norm": 0.2840973138809204,
|
| 990 |
-
"learning_rate": 0.001634695482043313,
|
| 991 |
-
"loss": 1.1919,
|
| 992 |
-
"step": 6600
|
| 993 |
-
},
|
| 994 |
-
{
|
| 995 |
-
"epoch": 28.448275862068964,
|
| 996 |
-
"eval_loss": 4.020354747772217,
|
| 997 |
-
"eval_runtime": 9.5176,
|
| 998 |
-
"eval_samples_per_second": 12434.937,
|
| 999 |
-
"eval_steps_per_second": 6.094,
|
| 1000 |
-
"step": 6600
|
| 1001 |
-
},
|
| 1002 |
-
{
|
| 1003 |
-
"epoch": 28.879310344827587,
|
| 1004 |
-
"grad_norm": 0.2763742208480835,
|
| 1005 |
-
"learning_rate": 0.0016241275672095395,
|
| 1006 |
-
"loss": 1.2454,
|
| 1007 |
-
"step": 6700
|
| 1008 |
-
},
|
| 1009 |
-
{
|
| 1010 |
-
"epoch": 28.879310344827587,
|
| 1011 |
-
"eval_loss": 3.929727792739868,
|
| 1012 |
-
"eval_runtime": 9.1984,
|
| 1013 |
-
"eval_samples_per_second": 12866.438,
|
| 1014 |
-
"eval_steps_per_second": 6.305,
|
| 1015 |
-
"step": 6700
|
| 1016 |
-
},
|
| 1017 |
-
{
|
| 1018 |
-
"epoch": 29.310344827586206,
|
| 1019 |
-
"grad_norm": 0.24317006766796112,
|
| 1020 |
-
"learning_rate": 0.0016134442160600903,
|
| 1021 |
-
"loss": 1.1954,
|
| 1022 |
-
"step": 6800
|
| 1023 |
-
},
|
| 1024 |
-
{
|
| 1025 |
-
"epoch": 29.310344827586206,
|
| 1026 |
-
"eval_loss": 4.102382659912109,
|
| 1027 |
-
"eval_runtime": 9.3618,
|
| 1028 |
-
"eval_samples_per_second": 12641.871,
|
| 1029 |
-
"eval_steps_per_second": 6.195,
|
| 1030 |
-
"step": 6800
|
| 1031 |
-
},
|
| 1032 |
-
{
|
| 1033 |
-
"epoch": 29.74137931034483,
|
| 1034 |
-
"grad_norm": 0.26351216435432434,
|
| 1035 |
-
"learning_rate": 0.0016026474045478978,
|
| 1036 |
-
"loss": 1.2149,
|
| 1037 |
-
"step": 6900
|
| 1038 |
-
},
|
| 1039 |
-
{
|
| 1040 |
-
"epoch": 29.74137931034483,
|
| 1041 |
-
"eval_loss": 4.013133525848389,
|
| 1042 |
-
"eval_runtime": 9.2046,
|
| 1043 |
-
"eval_samples_per_second": 12857.79,
|
| 1044 |
-
"eval_steps_per_second": 6.301,
|
| 1045 |
-
"step": 6900
|
| 1046 |
-
},
|
| 1047 |
-
{
|
| 1048 |
-
"epoch": 30.17241379310345,
|
| 1049 |
-
"grad_norm": 0.2500752806663513,
|
| 1050 |
-
"learning_rate": 0.0015917391296110992,
|
| 1051 |
-
"loss": 1.205,
|
| 1052 |
-
"step": 7000
|
| 1053 |
-
},
|
| 1054 |
-
{
|
| 1055 |
-
"epoch": 30.17241379310345,
|
| 1056 |
-
"eval_loss": 4.178187847137451,
|
| 1057 |
-
"eval_runtime": 9.2498,
|
| 1058 |
-
"eval_samples_per_second": 12794.992,
|
| 1059 |
-
"eval_steps_per_second": 6.27,
|
| 1060 |
-
"step": 7000
|
| 1061 |
-
},
|
| 1062 |
-
{
|
| 1063 |
-
"epoch": 30.603448275862068,
|
| 1064 |
-
"grad_norm": 0.27639082074165344,
|
| 1065 |
-
"learning_rate": 0.0015807214088036938,
|
| 1066 |
-
"loss": 1.1858,
|
| 1067 |
-
"step": 7100
|
| 1068 |
-
},
|
| 1069 |
-
{
|
| 1070 |
-
"epoch": 30.603448275862068,
|
| 1071 |
-
"eval_loss": 4.095057487487793,
|
| 1072 |
-
"eval_runtime": 9.5169,
|
| 1073 |
-
"eval_samples_per_second": 12435.848,
|
| 1074 |
-
"eval_steps_per_second": 6.094,
|
| 1075 |
-
"step": 7100
|
| 1076 |
-
},
|
| 1077 |
-
{
|
| 1078 |
-
"epoch": 31.03448275862069,
|
| 1079 |
-
"grad_norm": 0.2760908305644989,
|
| 1080 |
-
"learning_rate": 0.0015695962799223819,
|
| 1081 |
-
"loss": 1.2155,
|
| 1082 |
-
"step": 7200
|
| 1083 |
-
},
|
| 1084 |
-
{
|
| 1085 |
-
"epoch": 31.03448275862069,
|
| 1086 |
-
"eval_loss": 4.218206405639648,
|
| 1087 |
-
"eval_runtime": 9.2226,
|
| 1088 |
-
"eval_samples_per_second": 12832.692,
|
| 1089 |
-
"eval_steps_per_second": 6.289,
|
| 1090 |
-
"step": 7200
|
| 1091 |
-
},
|
| 1092 |
-
{
|
| 1093 |
-
"epoch": 31.46551724137931,
|
| 1094 |
-
"grad_norm": 0.28241831064224243,
|
| 1095 |
-
"learning_rate": 0.0015583658006296623,
|
| 1096 |
-
"loss": 1.1527,
|
| 1097 |
-
"step": 7300
|
| 1098 |
-
},
|
| 1099 |
-
{
|
| 1100 |
-
"epoch": 31.46551724137931,
|
| 1101 |
-
"eval_loss": 4.151749610900879,
|
| 1102 |
-
"eval_runtime": 9.4127,
|
| 1103 |
-
"eval_samples_per_second": 12573.563,
|
| 1104 |
-
"eval_steps_per_second": 6.162,
|
| 1105 |
-
"step": 7300
|
| 1106 |
-
},
|
| 1107 |
-
{
|
| 1108 |
-
"epoch": 31.896551724137932,
|
| 1109 |
-
"grad_norm": 0.28293758630752563,
|
| 1110 |
-
"learning_rate": 0.0015470320480732548,
|
| 1111 |
-
"loss": 1.2015,
|
| 1112 |
-
"step": 7400
|
| 1113 |
-
},
|
| 1114 |
-
{
|
| 1115 |
-
"epoch": 31.896551724137932,
|
| 1116 |
-
"eval_loss": 4.056530475616455,
|
| 1117 |
-
"eval_runtime": 9.2396,
|
| 1118 |
-
"eval_samples_per_second": 12809.071,
|
| 1119 |
-
"eval_steps_per_second": 6.277,
|
| 1120 |
-
"step": 7400
|
| 1121 |
-
},
|
| 1122 |
-
{
|
| 1123 |
-
"epoch": 32.327586206896555,
|
| 1124 |
-
"grad_norm": 0.26155322790145874,
|
| 1125 |
-
"learning_rate": 0.0015355971185019174,
|
| 1126 |
-
"loss": 1.1499,
|
| 1127 |
-
"step": 7500
|
| 1128 |
-
},
|
| 1129 |
-
{
|
| 1130 |
-
"epoch": 32.327586206896555,
|
| 1131 |
-
"eval_loss": 4.238384246826172,
|
| 1132 |
-
"eval_runtime": 9.2212,
|
| 1133 |
-
"eval_samples_per_second": 12834.667,
|
| 1134 |
-
"eval_steps_per_second": 6.29,
|
| 1135 |
-
"step": 7500
|
| 1136 |
-
},
|
| 1137 |
-
{
|
| 1138 |
-
"epoch": 32.758620689655174,
|
| 1139 |
-
"grad_norm": 0.26788121461868286,
|
| 1140 |
-
"learning_rate": 0.0015240631268777327,
|
| 1141 |
-
"loss": 1.1748,
|
| 1142 |
-
"step": 7600
|
| 1143 |
-
},
|
| 1144 |
-
{
|
| 1145 |
-
"epoch": 32.758620689655174,
|
| 1146 |
-
"eval_loss": 4.0977630615234375,
|
| 1147 |
-
"eval_runtime": 9.4085,
|
| 1148 |
-
"eval_samples_per_second": 12579.119,
|
| 1149 |
-
"eval_steps_per_second": 6.165,
|
| 1150 |
-
"step": 7600
|
| 1151 |
-
},
|
| 1152 |
-
{
|
| 1153 |
-
"epoch": 33.189655172413794,
|
| 1154 |
-
"grad_norm": 0.24862082302570343,
|
| 1155 |
-
"learning_rate": 0.0015124322064849342,
|
| 1156 |
-
"loss": 1.1615,
|
| 1157 |
-
"step": 7700
|
| 1158 |
-
},
|
| 1159 |
-
{
|
| 1160 |
-
"epoch": 33.189655172413794,
|
| 1161 |
-
"eval_loss": 4.326200008392334,
|
| 1162 |
-
"eval_runtime": 9.3683,
|
| 1163 |
-
"eval_samples_per_second": 12633.085,
|
| 1164 |
-
"eval_steps_per_second": 6.191,
|
| 1165 |
-
"step": 7700
|
| 1166 |
-
},
|
| 1167 |
-
{
|
| 1168 |
-
"epoch": 33.62068965517241,
|
| 1169 |
-
"grad_norm": 0.24566680192947388,
|
| 1170 |
-
"learning_rate": 0.0015007065085353387,
|
| 1171 |
-
"loss": 1.1482,
|
| 1172 |
-
"step": 7800
|
| 1173 |
-
},
|
| 1174 |
-
{
|
| 1175 |
-
"epoch": 33.62068965517241,
|
| 1176 |
-
"eval_loss": 4.191620826721191,
|
| 1177 |
-
"eval_runtime": 9.5145,
|
| 1178 |
-
"eval_samples_per_second": 12439.027,
|
| 1179 |
-
"eval_steps_per_second": 6.096,
|
| 1180 |
-
"step": 7800
|
| 1181 |
-
},
|
| 1182 |
-
{
|
| 1183 |
-
"epoch": 34.05172413793103,
|
| 1184 |
-
"grad_norm": 0.2441052347421646,
|
| 1185 |
-
"learning_rate": 0.001488888201770468,
|
| 1186 |
-
"loss": 1.1722,
|
| 1187 |
-
"step": 7900
|
| 1188 |
-
},
|
| 1189 |
-
{
|
| 1190 |
-
"epoch": 34.05172413793103,
|
| 1191 |
-
"eval_loss": 4.365562438964844,
|
| 1192 |
-
"eval_runtime": 9.2343,
|
| 1193 |
-
"eval_samples_per_second": 12816.408,
|
| 1194 |
-
"eval_steps_per_second": 6.281,
|
| 1195 |
-
"step": 7900
|
| 1196 |
-
},
|
| 1197 |
-
{
|
| 1198 |
-
"epoch": 34.48275862068966,
|
| 1199 |
-
"grad_norm": 0.2535702586174011,
|
| 1200 |
-
"learning_rate": 0.0014769794720604263,
|
| 1201 |
-
"loss": 1.1194,
|
| 1202 |
-
"step": 8000
|
| 1203 |
-
},
|
| 1204 |
-
{
|
| 1205 |
-
"epoch": 34.48275862068966,
|
| 1206 |
-
"eval_loss": 4.26139497756958,
|
| 1207 |
-
"eval_runtime": 9.2337,
|
| 1208 |
-
"eval_samples_per_second": 12817.319,
|
| 1209 |
-
"eval_steps_per_second": 6.281,
|
| 1210 |
-
"step": 8000
|
| 1211 |
-
},
|
| 1212 |
-
{
|
| 1213 |
-
"epoch": 34.91379310344828,
|
| 1214 |
-
"grad_norm": 0.25358447432518005,
|
| 1215 |
-
"learning_rate": 0.0014649825219996107,
|
| 1216 |
-
"loss": 1.1624,
|
| 1217 |
-
"step": 8100
|
| 1218 |
-
},
|
| 1219 |
-
{
|
| 1220 |
-
"epoch": 34.91379310344828,
|
| 1221 |
-
"eval_loss": 4.159610748291016,
|
| 1222 |
-
"eval_runtime": 9.3698,
|
| 1223 |
-
"eval_samples_per_second": 12631.093,
|
| 1224 |
-
"eval_steps_per_second": 6.19,
|
| 1225 |
-
"step": 8100
|
| 1226 |
-
},
|
| 1227 |
-
{
|
| 1228 |
-
"epoch": 35.3448275862069,
|
| 1229 |
-
"grad_norm": 0.2515275776386261,
|
| 1230 |
-
"learning_rate": 0.0014528995704993248,
|
| 1231 |
-
"loss": 1.1138,
|
| 1232 |
-
"step": 8200
|
| 1233 |
-
},
|
| 1234 |
-
{
|
| 1235 |
-
"epoch": 35.3448275862069,
|
| 1236 |
-
"eval_loss": 4.359853267669678,
|
| 1237 |
-
"eval_runtime": 9.249,
|
| 1238 |
-
"eval_samples_per_second": 12796.154,
|
| 1239 |
-
"eval_steps_per_second": 6.271,
|
| 1240 |
-
"step": 8200
|
| 1241 |
-
},
|
| 1242 |
-
{
|
| 1243 |
-
"epoch": 35.775862068965516,
|
| 1244 |
-
"grad_norm": 0.2827693819999695,
|
| 1245 |
-
"learning_rate": 0.0014407328523773804,
|
| 1246 |
-
"loss": 1.1399,
|
| 1247 |
-
"step": 8300
|
| 1248 |
-
},
|
| 1249 |
-
{
|
| 1250 |
-
"epoch": 35.775862068965516,
|
| 1251 |
-
"eval_loss": 4.250208377838135,
|
| 1252 |
-
"eval_runtime": 9.5293,
|
| 1253 |
-
"eval_samples_per_second": 12419.637,
|
| 1254 |
-
"eval_steps_per_second": 6.086,
|
| 1255 |
-
"step": 8300
|
| 1256 |
-
},
|
| 1257 |
-
{
|
| 1258 |
-
"epoch": 36.206896551724135,
|
| 1259 |
-
"grad_norm": 0.25135308504104614,
|
| 1260 |
-
"learning_rate": 0.0014284846179447514,
|
| 1261 |
-
"loss": 1.1223,
|
| 1262 |
-
"step": 8400
|
| 1263 |
-
},
|
| 1264 |
-
{
|
| 1265 |
-
"epoch": 36.206896551724135,
|
| 1266 |
-
"eval_loss": 4.41204833984375,
|
| 1267 |
-
"eval_runtime": 9.2023,
|
| 1268 |
-
"eval_samples_per_second": 12861.028,
|
| 1269 |
-
"eval_steps_per_second": 6.303,
|
| 1270 |
-
"step": 8400
|
| 1271 |
-
},
|
| 1272 |
-
{
|
| 1273 |
-
"epoch": 36.63793103448276,
|
| 1274 |
-
"grad_norm": 0.2558540999889374,
|
| 1275 |
-
"learning_rate": 0.0014161571325893665,
|
| 1276 |
-
"loss": 1.1157,
|
| 1277 |
-
"step": 8500
|
| 1278 |
-
},
|
| 1279 |
-
{
|
| 1280 |
-
"epoch": 36.63793103448276,
|
| 1281 |
-
"eval_loss": 4.329861640930176,
|
| 1282 |
-
"eval_runtime": 9.2024,
|
| 1283 |
-
"eval_samples_per_second": 12860.85,
|
| 1284 |
-
"eval_steps_per_second": 6.303,
|
| 1285 |
-
"step": 8500
|
| 1286 |
-
},
|
| 1287 |
-
{
|
| 1288 |
-
"epoch": 37.06896551724138,
|
| 1289 |
-
"grad_norm": 0.23830156028270721,
|
| 1290 |
-
"learning_rate": 0.0014037526763571095,
|
| 1291 |
-
"loss": 1.1328,
|
| 1292 |
-
"step": 8600
|
| 1293 |
-
},
|
| 1294 |
-
{
|
| 1295 |
-
"epoch": 37.06896551724138,
|
| 1296 |
-
"eval_loss": 4.509239673614502,
|
| 1297 |
-
"eval_runtime": 9.3506,
|
| 1298 |
-
"eval_samples_per_second": 12657.0,
|
| 1299 |
-
"eval_steps_per_second": 6.203,
|
| 1300 |
-
"step": 8600
|
| 1301 |
-
},
|
| 1302 |
-
{
|
| 1303 |
-
"epoch": 37.5,
|
| 1304 |
-
"grad_norm": 0.24350416660308838,
|
| 1305 |
-
"learning_rate": 0.0013912735435301126,
|
| 1306 |
-
"loss": 1.0913,
|
| 1307 |
-
"step": 8700
|
| 1308 |
-
},
|
| 1309 |
-
{
|
| 1310 |
-
"epoch": 37.5,
|
| 1311 |
-
"eval_loss": 4.415010452270508,
|
| 1312 |
-
"eval_runtime": 9.2551,
|
| 1313 |
-
"eval_samples_per_second": 12787.61,
|
| 1314 |
-
"eval_steps_per_second": 6.267,
|
| 1315 |
-
"step": 8700
|
| 1316 |
-
},
|
| 1317 |
-
{
|
| 1318 |
-
"epoch": 37.93103448275862,
|
| 1319 |
-
"grad_norm": 0.27101027965545654,
|
| 1320 |
-
"learning_rate": 0.0013787220422024134,
|
| 1321 |
-
"loss": 1.1287,
|
| 1322 |
-
"step": 8800
|
| 1323 |
-
},
|
| 1324 |
-
{
|
| 1325 |
-
"epoch": 37.93103448275862,
|
| 1326 |
-
"eval_loss": 4.311288833618164,
|
| 1327 |
-
"eval_runtime": 9.5314,
|
| 1328 |
-
"eval_samples_per_second": 12416.995,
|
| 1329 |
-
"eval_steps_per_second": 6.085,
|
| 1330 |
-
"step": 8800
|
| 1331 |
-
},
|
| 1332 |
-
{
|
| 1333 |
-
"epoch": 38.36206896551724,
|
| 1334 |
-
"grad_norm": 0.23868116736412048,
|
| 1335 |
-
"learning_rate": 0.0013661004938530573,
|
| 1336 |
-
"loss": 1.0804,
|
| 1337 |
-
"step": 8900
|
| 1338 |
-
},
|
| 1339 |
-
{
|
| 1340 |
-
"epoch": 38.36206896551724,
|
| 1341 |
-
"eval_loss": 4.474818229675293,
|
| 1342 |
-
"eval_runtime": 9.2149,
|
| 1343 |
-
"eval_samples_per_second": 12843.381,
|
| 1344 |
-
"eval_steps_per_second": 6.294,
|
| 1345 |
-
"step": 8900
|
| 1346 |
-
},
|
| 1347 |
-
{
|
| 1348 |
-
"epoch": 38.793103448275865,
|
| 1349 |
-
"grad_norm": 0.2615257799625397,
|
| 1350 |
-
"learning_rate": 0.0013534112329167277,
|
| 1351 |
-
"loss": 1.1087,
|
| 1352 |
-
"step": 9000
|
| 1353 |
-
},
|
| 1354 |
-
{
|
| 1355 |
-
"epoch": 38.793103448275865,
|
| 1356 |
-
"eval_loss": 4.382425308227539,
|
| 1357 |
-
"eval_runtime": 9.2362,
|
| 1358 |
-
"eval_samples_per_second": 12813.759,
|
| 1359 |
-
"eval_steps_per_second": 6.28,
|
| 1360 |
-
"step": 9000
|
| 1361 |
-
},
|
| 1362 |
-
{
|
| 1363 |
-
"epoch": 39.224137931034484,
|
| 1364 |
-
"grad_norm": 0.23843148350715637,
|
| 1365 |
-
"learning_rate": 0.0013406566063519764,
|
| 1366 |
-
"loss": 1.0892,
|
| 1367 |
-
"step": 9100
|
| 1368 |
-
},
|
| 1369 |
-
{
|
| 1370 |
-
"epoch": 39.224137931034484,
|
| 1371 |
-
"eval_loss": 4.5527825355529785,
|
| 1372 |
-
"eval_runtime": 9.4035,
|
| 1373 |
-
"eval_samples_per_second": 12585.803,
|
| 1374 |
-
"eval_steps_per_second": 6.168,
|
| 1375 |
-
"step": 9100
|
| 1376 |
-
},
|
| 1377 |
-
{
|
| 1378 |
-
"epoch": 39.6551724137931,
|
| 1379 |
-
"grad_norm": 0.2602212131023407,
|
| 1380 |
-
"learning_rate": 0.0013278389732071388,
|
| 1381 |
-
"loss": 1.0872,
|
| 1382 |
-
"step": 9200
|
| 1383 |
-
},
|
| 1384 |
-
{
|
| 1385 |
-
"epoch": 39.6551724137931,
|
| 1386 |
-
"eval_loss": 4.4413909912109375,
|
| 1387 |
-
"eval_runtime": 9.2185,
|
| 1388 |
-
"eval_samples_per_second": 12838.457,
|
| 1389 |
-
"eval_steps_per_second": 6.292,
|
| 1390 |
-
"step": 9200
|
| 1391 |
-
},
|
| 1392 |
-
{
|
| 1393 |
-
"epoch": 40.08620689655172,
|
| 1394 |
-
"grad_norm": 0.2304549515247345,
|
| 1395 |
-
"learning_rate": 0.0013149607041840125,
|
| 1396 |
-
"loss": 1.0997,
|
| 1397 |
-
"step": 9300
|
| 1398 |
-
},
|
| 1399 |
-
{
|
| 1400 |
-
"epoch": 40.08620689655172,
|
| 1401 |
-
"eval_loss": 4.610817909240723,
|
| 1402 |
-
"eval_runtime": 9.3893,
|
| 1403 |
-
"eval_samples_per_second": 12604.936,
|
| 1404 |
-
"eval_steps_per_second": 6.177,
|
| 1405 |
-
"step": 9300
|
| 1406 |
-
},
|
| 1407 |
-
{
|
| 1408 |
-
"epoch": 40.51724137931034,
|
| 1409 |
-
"grad_norm": 0.24227924644947052,
|
| 1410 |
-
"learning_rate": 0.0013020241811993831,
|
| 1411 |
-
"loss": 1.0649,
|
| 1412 |
-
"step": 9400
|
| 1413 |
-
},
|
| 1414 |
-
{
|
| 1415 |
-
"epoch": 40.51724137931034,
|
| 1416 |
-
"eval_loss": 4.493175506591797,
|
| 1417 |
-
"eval_runtime": 9.3864,
|
| 1418 |
-
"eval_samples_per_second": 12608.751,
|
| 1419 |
-
"eval_steps_per_second": 6.179,
|
| 1420 |
-
"step": 9400
|
| 1421 |
-
},
|
| 1422 |
-
{
|
| 1423 |
-
"epoch": 40.94827586206897,
|
| 1424 |
-
"grad_norm": 0.28171467781066895,
|
| 1425 |
-
"learning_rate": 0.0012890317969444715,
|
| 1426 |
-
"loss": 1.1007,
|
| 1427 |
-
"step": 9500
|
| 1428 |
-
},
|
| 1429 |
-
{
|
| 1430 |
-
"epoch": 40.94827586206897,
|
| 1431 |
-
"eval_loss": 4.4659504890441895,
|
| 1432 |
-
"eval_runtime": 9.3378,
|
| 1433 |
-
"eval_samples_per_second": 12674.445,
|
| 1434 |
-
"eval_steps_per_second": 6.211,
|
| 1435 |
-
"step": 9500
|
| 1436 |
-
},
|
| 1437 |
-
{
|
| 1438 |
-
"epoch": 41.37931034482759,
|
| 1439 |
-
"grad_norm": 0.22989529371261597,
|
| 1440 |
-
"learning_rate": 0.0012759859544423924,
|
| 1441 |
-
"loss": 1.0526,
|
| 1442 |
-
"step": 9600
|
| 1443 |
-
},
|
| 1444 |
-
{
|
| 1445 |
-
"epoch": 41.37931034482759,
|
| 1446 |
-
"eval_loss": 4.579300880432129,
|
| 1447 |
-
"eval_runtime": 9.346,
|
| 1448 |
-
"eval_samples_per_second": 12663.266,
|
| 1449 |
-
"eval_steps_per_second": 6.206,
|
| 1450 |
-
"step": 9600
|
| 1451 |
-
},
|
| 1452 |
-
{
|
| 1453 |
-
"epoch": 41.810344827586206,
|
| 1454 |
-
"grad_norm": 0.22905075550079346,
|
| 1455 |
-
"learning_rate": 0.001262889066603698,
|
| 1456 |
-
"loss": 1.0816,
|
| 1457 |
-
"step": 9700
|
| 1458 |
-
},
|
| 1459 |
-
{
|
| 1460 |
-
"epoch": 41.810344827586206,
|
| 1461 |
-
"eval_loss": 4.495105743408203,
|
| 1462 |
-
"eval_runtime": 9.2447,
|
| 1463 |
-
"eval_samples_per_second": 12802.093,
|
| 1464 |
-
"eval_steps_per_second": 6.274,
|
| 1465 |
-
"step": 9700
|
| 1466 |
-
},
|
| 1467 |
-
{
|
| 1468 |
-
"epoch": 42.241379310344826,
|
| 1469 |
-
"grad_norm": 0.23457792401313782,
|
| 1470 |
-
"learning_rate": 0.0012497435557800973,
|
| 1471 |
-
"loss": 1.0612,
|
| 1472 |
-
"step": 9800
|
| 1473 |
-
},
|
| 1474 |
-
{
|
| 1475 |
-
"epoch": 42.241379310344826,
|
| 1476 |
-
"eval_loss": 4.662010192871094,
|
| 1477 |
-
"eval_runtime": 9.3901,
|
| 1478 |
-
"eval_samples_per_second": 12603.862,
|
| 1479 |
-
"eval_steps_per_second": 6.177,
|
| 1480 |
-
"step": 9800
|
| 1481 |
-
},
|
| 1482 |
-
{
|
| 1483 |
-
"epoch": 42.672413793103445,
|
| 1484 |
-
"grad_norm": 0.24168674647808075,
|
| 1485 |
-
"learning_rate": 0.0012365518533164264,
|
| 1486 |
-
"loss": 1.0609,
|
| 1487 |
-
"step": 9900
|
| 1488 |
-
},
|
| 1489 |
-
{
|
| 1490 |
-
"epoch": 42.672413793103445,
|
| 1491 |
-
"eval_loss": 4.597413539886475,
|
| 1492 |
-
"eval_runtime": 9.2147,
|
| 1493 |
-
"eval_samples_per_second": 12843.706,
|
| 1494 |
-
"eval_steps_per_second": 6.294,
|
| 1495 |
-
"step": 9900
|
| 1496 |
-
},
|
| 1497 |
-
{
|
| 1498 |
-
"epoch": 43.10344827586207,
|
| 1499 |
-
"grad_norm": 0.25161978602409363,
|
| 1500 |
-
"learning_rate": 0.0012233163991009536,
|
| 1501 |
-
"loss": 1.0705,
|
| 1502 |
-
"step": 10000
|
| 1503 |
-
},
|
| 1504 |
-
{
|
| 1505 |
-
"epoch": 43.10344827586207,
|
| 1506 |
-
"eval_loss": 4.722944736480713,
|
| 1507 |
-
"eval_runtime": 9.377,
|
| 1508 |
-
"eval_samples_per_second": 12621.406,
|
| 1509 |
-
"eval_steps_per_second": 6.185,
|
| 1510 |
-
"step": 10000
|
| 1511 |
-
},
|
| 1512 |
-
{
|
| 1513 |
-
"epoch": 43.53448275862069,
|
| 1514 |
-
"grad_norm": 0.2435440868139267,
|
| 1515 |
-
"learning_rate": 0.0012100396411141104,
|
| 1516 |
-
"loss": 1.0413,
|
| 1517 |
-
"step": 10100
|
| 1518 |
-
},
|
| 1519 |
-
{
|
| 1520 |
-
"epoch": 43.53448275862069,
|
| 1521 |
-
"eval_loss": 4.6760735511779785,
|
| 1522 |
-
"eval_runtime": 9.4169,
|
| 1523 |
-
"eval_samples_per_second": 12567.971,
|
| 1524 |
-
"eval_steps_per_second": 6.159,
|
| 1525 |
-
"step": 10100
|
| 1526 |
-
},
|
| 1527 |
-
{
|
| 1528 |
-
"epoch": 43.96551724137931,
|
| 1529 |
-
"grad_norm": 0.22854387760162354,
|
| 1530 |
-
"learning_rate": 0.0011967240349757202,
|
| 1531 |
-
"loss": 1.075,
|
| 1532 |
-
"step": 10200
|
| 1533 |
-
},
|
| 1534 |
-
{
|
| 1535 |
-
"epoch": 43.96551724137931,
|
| 1536 |
-
"eval_loss": 4.56270170211792,
|
| 1537 |
-
"eval_runtime": 9.2186,
|
| 1538 |
-
"eval_samples_per_second": 12838.229,
|
| 1539 |
-
"eval_steps_per_second": 6.292,
|
| 1540 |
-
"step": 10200
|
| 1541 |
-
},
|
| 1542 |
-
{
|
| 1543 |
-
"epoch": 44.39655172413793,
|
| 1544 |
-
"grad_norm": 0.22642293572425842,
|
| 1545 |
-
"learning_rate": 0.001183372043490815,
|
| 1546 |
-
"loss": 1.0275,
|
| 1547 |
-
"step": 10300
|
| 1548 |
-
},
|
| 1549 |
-
{
|
| 1550 |
-
"epoch": 44.39655172413793,
|
| 1551 |
-
"eval_loss": 4.700027942657471,
|
| 1552 |
-
"eval_runtime": 9.3756,
|
| 1553 |
-
"eval_samples_per_second": 12623.278,
|
| 1554 |
-
"eval_steps_per_second": 6.186,
|
| 1555 |
-
"step": 10300
|
| 1556 |
-
},
|
| 1557 |
-
{
|
| 1558 |
-
"epoch": 44.827586206896555,
|
| 1559 |
-
"grad_norm": 0.2266691029071808,
|
| 1560 |
-
"learning_rate": 0.0011699861361941259,
|
| 1561 |
-
"loss": 1.0559,
|
| 1562 |
-
"step": 10400
|
| 1563 |
-
},
|
| 1564 |
-
{
|
| 1565 |
-
"epoch": 44.827586206896555,
|
| 1566 |
-
"eval_loss": 4.6264777183532715,
|
| 1567 |
-
"eval_runtime": 9.2603,
|
| 1568 |
-
"eval_samples_per_second": 12780.536,
|
| 1569 |
-
"eval_steps_per_second": 6.263,
|
| 1570 |
-
"step": 10400
|
| 1571 |
-
},
|
| 1572 |
-
{
|
| 1573 |
-
"epoch": 45.258620689655174,
|
| 1574 |
-
"grad_norm": 0.21492455899715424,
|
| 1575 |
-
"learning_rate": 0.0011565687888933276,
|
| 1576 |
-
"loss": 1.0347,
|
| 1577 |
-
"step": 10500
|
| 1578 |
-
},
|
| 1579 |
-
{
|
| 1580 |
-
"epoch": 45.258620689655174,
|
| 1581 |
-
"eval_loss": 4.728958606719971,
|
| 1582 |
-
"eval_runtime": 9.3904,
|
| 1583 |
-
"eval_samples_per_second": 12603.413,
|
| 1584 |
-
"eval_steps_per_second": 6.177,
|
| 1585 |
-
"step": 10500
|
| 1586 |
-
},
|
| 1587 |
-
{
|
| 1588 |
-
"epoch": 45.689655172413794,
|
| 1589 |
-
"grad_norm": 0.21673394739627838,
|
| 1590 |
-
"learning_rate": 0.0011431224832111197,
|
| 1591 |
-
"loss": 1.0399,
|
| 1592 |
-
"step": 10600
|
| 1593 |
-
},
|
| 1594 |
-
{
|
| 1595 |
-
"epoch": 45.689655172413794,
|
| 1596 |
-
"eval_loss": 4.708123207092285,
|
| 1597 |
-
"eval_runtime": 9.2682,
|
| 1598 |
-
"eval_samples_per_second": 12769.564,
|
| 1599 |
-
"eval_steps_per_second": 6.258,
|
| 1600 |
-
"step": 10600
|
| 1601 |
-
},
|
| 1602 |
-
{
|
| 1603 |
-
"epoch": 46.12068965517241,
|
| 1604 |
-
"grad_norm": 0.22129711508750916,
|
| 1605 |
-
"learning_rate": 0.0011296497061262364,
|
| 1606 |
-
"loss": 1.0426,
|
| 1607 |
-
"step": 10700
|
| 1608 |
-
},
|
| 1609 |
-
{
|
| 1610 |
-
"epoch": 46.12068965517241,
|
| 1611 |
-
"eval_loss": 4.850292205810547,
|
| 1612 |
-
"eval_runtime": 9.2246,
|
| 1613 |
-
"eval_samples_per_second": 12829.961,
|
| 1614 |
-
"eval_steps_per_second": 6.288,
|
| 1615 |
-
"step": 10700
|
| 1616 |
-
},
|
| 1617 |
-
{
|
| 1618 |
-
"epoch": 46.55172413793103,
|
| 1619 |
-
"grad_norm": 0.24281208217144012,
|
| 1620 |
-
"learning_rate": 0.0011161529495134655,
|
| 1621 |
-
"loss": 1.0222,
|
| 1622 |
-
"step": 10800
|
| 1623 |
-
},
|
| 1624 |
-
{
|
| 1625 |
-
"epoch": 46.55172413793103,
|
| 1626 |
-
"eval_loss": 4.75180196762085,
|
| 1627 |
-
"eval_runtime": 9.3686,
|
| 1628 |
-
"eval_samples_per_second": 12632.692,
|
| 1629 |
-
"eval_steps_per_second": 6.191,
|
| 1630 |
-
"step": 10800
|
| 1631 |
-
},
|
| 1632 |
-
{
|
| 1633 |
-
"epoch": 46.98275862068966,
|
| 1634 |
-
"grad_norm": 0.24109460413455963,
|
| 1635 |
-
"learning_rate": 0.0011026347096827578,
|
| 1636 |
-
"loss": 1.05,
|
| 1637 |
-
"step": 10900
|
| 1638 |
-
},
|
| 1639 |
-
{
|
| 1640 |
-
"epoch": 46.98275862068966,
|
| 1641 |
-
"eval_loss": 4.682476043701172,
|
| 1642 |
-
"eval_runtime": 9.3818,
|
| 1643 |
-
"eval_samples_per_second": 12614.995,
|
| 1644 |
-
"eval_steps_per_second": 6.182,
|
| 1645 |
-
"step": 10900
|
| 1646 |
-
},
|
| 1647 |
-
{
|
| 1648 |
-
"epoch": 47.41379310344828,
|
| 1649 |
-
"grad_norm": 0.26203250885009766,
|
| 1650 |
-
"learning_rate": 0.0010890974869175213,
|
| 1651 |
-
"loss": 1.0048,
|
| 1652 |
-
"step": 11000
|
| 1653 |
-
},
|
| 1654 |
-
{
|
| 1655 |
-
"epoch": 47.41379310344828,
|
| 1656 |
-
"eval_loss": 4.7717461585998535,
|
| 1657 |
-
"eval_runtime": 9.2238,
|
| 1658 |
-
"eval_samples_per_second": 12831.044,
|
| 1659 |
-
"eval_steps_per_second": 6.288,
|
| 1660 |
-
"step": 11000
|
| 1661 |
-
},
|
| 1662 |
-
{
|
| 1663 |
-
"epoch": 47.8448275862069,
|
| 1664 |
-
"grad_norm": 0.22025622427463531,
|
| 1665 |
-
"learning_rate": 0.001075543785012176,
|
| 1666 |
-
"loss": 1.0356,
|
| 1667 |
-
"step": 11100
|
| 1668 |
-
},
|
| 1669 |
-
{
|
| 1670 |
-
"epoch": 47.8448275862069,
|
| 1671 |
-
"eval_loss": 4.745931148529053,
|
| 1672 |
-
"eval_runtime": 9.3379,
|
| 1673 |
-
"eval_samples_per_second": 12674.319,
|
| 1674 |
-
"eval_steps_per_second": 6.211,
|
| 1675 |
-
"step": 11100
|
| 1676 |
-
},
|
| 1677 |
-
{
|
| 1678 |
-
"epoch": 48.275862068965516,
|
| 1679 |
-
"grad_norm": 0.2139374315738678,
|
| 1680 |
-
"learning_rate": 0.0010619761108090632,
|
| 1681 |
-
"loss": 1.0127,
|
| 1682 |
-
"step": 11200
|
| 1683 |
-
},
|
| 1684 |
-
{
|
| 1685 |
-
"epoch": 48.275862068965516,
|
| 1686 |
-
"eval_loss": 4.8763251304626465,
|
| 1687 |
-
"eval_runtime": 9.1962,
|
| 1688 |
-
"eval_samples_per_second": 12869.532,
|
| 1689 |
-
"eval_steps_per_second": 6.307,
|
| 1690 |
-
"step": 11200
|
| 1691 |
-
},
|
| 1692 |
-
{
|
| 1693 |
-
"epoch": 48.706896551724135,
|
| 1694 |
-
"grad_norm": 0.21663136780261993,
|
| 1695 |
-
"learning_rate": 0.0010483969737347882,
|
| 1696 |
-
"loss": 1.0203,
|
| 1697 |
-
"step": 11300
|
| 1698 |
-
},
|
| 1699 |
-
{
|
| 1700 |
-
"epoch": 48.706896551724135,
|
| 1701 |
-
"eval_loss": 4.779572010040283,
|
| 1702 |
-
"eval_runtime": 9.2083,
|
| 1703 |
-
"eval_samples_per_second": 12852.706,
|
| 1704 |
-
"eval_steps_per_second": 6.299,
|
| 1705 |
-
"step": 11300
|
| 1706 |
-
},
|
| 1707 |
-
{
|
| 1708 |
-
"epoch": 49.13793103448276,
|
| 1709 |
-
"grad_norm": 0.19012530148029327,
|
| 1710 |
-
"learning_rate": 0.0010348088853360865,
|
| 1711 |
-
"loss": 1.0188,
|
| 1712 |
-
"step": 11400
|
| 1713 |
-
},
|
| 1714 |
-
{
|
| 1715 |
-
"epoch": 49.13793103448276,
|
| 1716 |
-
"eval_loss": 4.949375629425049,
|
| 1717 |
-
"eval_runtime": 9.4015,
|
| 1718 |
-
"eval_samples_per_second": 12588.477,
|
| 1719 |
-
"eval_steps_per_second": 6.169,
|
| 1720 |
-
"step": 11400
|
| 1721 |
-
},
|
| 1722 |
-
{
|
| 1723 |
-
"epoch": 49.56896551724138,
|
| 1724 |
-
"grad_norm": 0.21295411884784698,
|
| 1725 |
-
"learning_rate": 0.0010212143588152972,
|
| 1726 |
-
"loss": 1.0028,
|
| 1727 |
-
"step": 11500
|
| 1728 |
-
},
|
| 1729 |
-
{
|
| 1730 |
-
"epoch": 49.56896551724138,
|
| 1731 |
-
"eval_loss": 4.887173652648926,
|
| 1732 |
-
"eval_runtime": 9.2299,
|
| 1733 |
-
"eval_samples_per_second": 12822.585,
|
| 1734 |
-
"eval_steps_per_second": 6.284,
|
| 1735 |
-
"step": 11500
|
| 1736 |
-
},
|
| 1737 |
-
{
|
| 1738 |
-
"epoch": 50.0,
|
| 1739 |
-
"grad_norm": 0.2105313092470169,
|
| 1740 |
-
"learning_rate": 0.0010076159085655307,
|
| 1741 |
-
"loss": 1.0284,
|
| 1742 |
-
"step": 11600
|
| 1743 |
-
},
|
| 1744 |
-
{
|
| 1745 |
-
"epoch": 50.0,
|
| 1746 |
-
"eval_loss": 4.840916633605957,
|
| 1747 |
-
"eval_runtime": 9.517,
|
| 1748 |
-
"eval_samples_per_second": 12435.741,
|
| 1749 |
-
"eval_steps_per_second": 6.094,
|
| 1750 |
-
"step": 11600
|
| 1751 |
-
},
|
| 1752 |
-
{
|
| 1753 |
-
"epoch": 50.43103448275862,
|
| 1754 |
-
"grad_norm": 0.20751339197158813,
|
| 1755 |
-
"learning_rate": 0.0009940160497056154,
|
| 1756 |
-
"loss": 0.986,
|
| 1757 |
-
"step": 11700
|
| 1758 |
-
},
|
| 1759 |
-
{
|
| 1760 |
-
"epoch": 50.43103448275862,
|
| 1761 |
-
"eval_loss": 4.903811931610107,
|
| 1762 |
-
"eval_runtime": 9.2176,
|
| 1763 |
-
"eval_samples_per_second": 12839.722,
|
| 1764 |
-
"eval_steps_per_second": 6.292,
|
| 1765 |
-
"step": 11700
|
| 1766 |
-
},
|
| 1767 |
-
{
|
| 1768 |
-
"epoch": 50.86206896551724,
|
| 1769 |
-
"grad_norm": 0.22046105563640594,
|
| 1770 |
-
"learning_rate": 0.0009804172976149107,
|
| 1771 |
-
"loss": 1.015,
|
| 1772 |
-
"step": 11800
|
| 1773 |
-
},
|
| 1774 |
-
{
|
| 1775 |
-
"epoch": 50.86206896551724,
|
| 1776 |
-
"eval_loss": 4.859233379364014,
|
| 1777 |
-
"eval_runtime": 9.2588,
|
| 1778 |
-
"eval_samples_per_second": 12782.512,
|
| 1779 |
-
"eval_steps_per_second": 6.264,
|
| 1780 |
-
"step": 11800
|
| 1781 |
-
},
|
| 1782 |
-
{
|
| 1783 |
-
"epoch": 51.293103448275865,
|
| 1784 |
-
"grad_norm": 0.20184583961963654,
|
| 1785 |
-
"learning_rate": 0.0009668221674680736,
|
| 1786 |
-
"loss": 0.9919,
|
| 1787 |
-
"step": 11900
|
| 1788 |
-
},
|
| 1789 |
-
{
|
| 1790 |
-
"epoch": 51.293103448275865,
|
| 1791 |
-
"eval_loss": 4.959497451782227,
|
| 1792 |
-
"eval_runtime": 9.4293,
|
| 1793 |
-
"eval_samples_per_second": 12551.434,
|
| 1794 |
-
"eval_steps_per_second": 6.151,
|
| 1795 |
-
"step": 11900
|
| 1796 |
-
},
|
| 1797 |
-
{
|
| 1798 |
-
"epoch": 51.724137931034484,
|
| 1799 |
-
"grad_norm": 0.19977693259716034,
|
| 1800 |
-
"learning_rate": 0.0009532331737698578,
|
| 1801 |
-
"loss": 1.001,
|
| 1802 |
-
"step": 12000
|
| 1803 |
-
},
|
| 1804 |
-
{
|
| 1805 |
-
"epoch": 51.724137931034484,
|
| 1806 |
-
"eval_loss": 4.924416542053223,
|
| 1807 |
-
"eval_runtime": 9.2287,
|
| 1808 |
-
"eval_samples_per_second": 12824.178,
|
| 1809 |
-
"eval_steps_per_second": 6.285,
|
| 1810 |
-
"step": 12000
|
| 1811 |
-
},
|
| 1812 |
-
{
|
| 1813 |
-
"epoch": 52.1551724137931,
|
| 1814 |
-
"grad_norm": 0.20899131894111633,
|
| 1815 |
-
"learning_rate": 0.0009396528298900436,
|
| 1816 |
-
"loss": 0.9974,
|
| 1817 |
-
"step": 12100
|
| 1818 |
-
},
|
| 1819 |
-
{
|
| 1820 |
-
"epoch": 52.1551724137931,
|
| 1821 |
-
"eval_loss": 5.01582670211792,
|
| 1822 |
-
"eval_runtime": 9.5191,
|
| 1823 |
-
"eval_samples_per_second": 12432.95,
|
| 1824 |
-
"eval_steps_per_second": 6.093,
|
| 1825 |
-
"step": 12100
|
| 1826 |
-
},
|
| 1827 |
-
{
|
| 1828 |
-
"epoch": 52.58620689655172,
|
| 1829 |
-
"grad_norm": 0.20686785876750946,
|
| 1830 |
-
"learning_rate": 0.0009260836475985731,
|
| 1831 |
-
"loss": 0.9863,
|
| 1832 |
-
"step": 12200
|
| 1833 |
-
},
|
| 1834 |
-
{
|
| 1835 |
-
"epoch": 52.58620689655172,
|
| 1836 |
-
"eval_loss": 4.9655070304870605,
|
| 1837 |
-
"eval_runtime": 9.2685,
|
| 1838 |
-
"eval_samples_per_second": 12769.132,
|
| 1839 |
-
"eval_steps_per_second": 6.258,
|
| 1840 |
-
"step": 12200
|
| 1841 |
-
},
|
| 1842 |
-
{
|
| 1843 |
-
"epoch": 53.01724137931034,
|
| 1844 |
-
"grad_norm": 0.20469722151756287,
|
| 1845 |
-
"learning_rate": 0.0009125281366009814,
|
| 1846 |
-
"loss": 1.0061,
|
| 1847 |
-
"step": 12300
|
| 1848 |
-
},
|
| 1849 |
-
{
|
| 1850 |
-
"epoch": 53.01724137931034,
|
| 1851 |
-
"eval_loss": 5.180333137512207,
|
| 1852 |
-
"eval_runtime": 9.266,
|
| 1853 |
-
"eval_samples_per_second": 12772.604,
|
| 1854 |
-
"eval_steps_per_second": 6.259,
|
| 1855 |
-
"step": 12300
|
| 1856 |
-
},
|
| 1857 |
-
{
|
| 1858 |
-
"epoch": 53.44827586206897,
|
| 1859 |
-
"grad_norm": 0.1923903524875641,
|
| 1860 |
-
"learning_rate": 0.0008989888040742127,
|
| 1861 |
-
"loss": 0.971,
|
| 1862 |
-
"step": 12400
|
| 1863 |
-
},
|
| 1864 |
-
{
|
| 1865 |
-
"epoch": 53.44827586206897,
|
| 1866 |
-
"eval_loss": 4.984365463256836,
|
| 1867 |
-
"eval_runtime": 9.4114,
|
| 1868 |
-
"eval_samples_per_second": 12575.325,
|
| 1869 |
-
"eval_steps_per_second": 6.163,
|
| 1870 |
-
"step": 12400
|
| 1871 |
-
},
|
| 1872 |
-
{
|
| 1873 |
-
"epoch": 53.87931034482759,
|
| 1874 |
-
"grad_norm": 0.2009354680776596,
|
| 1875 |
-
"learning_rate": 0.0008854681542029017,
|
| 1876 |
-
"loss": 0.9965,
|
| 1877 |
-
"step": 12500
|
| 1878 |
-
},
|
| 1879 |
-
{
|
| 1880 |
-
"epoch": 53.87931034482759,
|
| 1881 |
-
"eval_loss": 4.9768877029418945,
|
| 1882 |
-
"eval_runtime": 9.2039,
|
| 1883 |
-
"eval_samples_per_second": 12858.815,
|
| 1884 |
-
"eval_steps_per_second": 6.302,
|
| 1885 |
-
"step": 12500
|
| 1886 |
-
},
|
| 1887 |
-
{
|
| 1888 |
-
"epoch": 54.310344827586206,
|
| 1889 |
-
"grad_norm": 0.2066151350736618,
|
| 1890 |
-
"learning_rate": 0.0008719686877162076,
|
| 1891 |
-
"loss": 0.9717,
|
| 1892 |
-
"step": 12600
|
| 1893 |
-
},
|
| 1894 |
-
{
|
| 1895 |
-
"epoch": 54.310344827586206,
|
| 1896 |
-
"eval_loss": 5.092445373535156,
|
| 1897 |
-
"eval_runtime": 9.5207,
|
| 1898 |
-
"eval_samples_per_second": 12430.879,
|
| 1899 |
-
"eval_steps_per_second": 6.092,
|
| 1900 |
-
"step": 12600
|
| 1901 |
-
},
|
| 1902 |
-
{
|
| 1903 |
-
"epoch": 54.741379310344826,
|
| 1904 |
-
"grad_norm": 0.1960015892982483,
|
| 1905 |
-
"learning_rate": 0.0008584929014252898,
|
| 1906 |
-
"loss": 0.9842,
|
| 1907 |
-
"step": 12700
|
| 1908 |
-
},
|
| 1909 |
-
{
|
| 1910 |
-
"epoch": 54.741379310344826,
|
| 1911 |
-
"eval_loss": 4.997062683105469,
|
| 1912 |
-
"eval_runtime": 9.2008,
|
| 1913 |
-
"eval_samples_per_second": 12863.189,
|
| 1914 |
-
"eval_steps_per_second": 6.304,
|
| 1915 |
-
"step": 12700
|
| 1916 |
-
},
|
| 1917 |
-
{
|
| 1918 |
-
"epoch": 55.172413793103445,
|
| 1919 |
-
"grad_norm": 0.19153521955013275,
|
| 1920 |
-
"learning_rate": 0.0008450432877615072,
|
| 1921 |
-
"loss": 0.9782,
|
| 1922 |
-
"step": 12800
|
| 1923 |
-
},
|
| 1924 |
-
{
|
| 1925 |
-
"epoch": 55.172413793103445,
|
| 1926 |
-
"eval_loss": 5.148665428161621,
|
| 1927 |
-
"eval_runtime": 9.203,
|
| 1928 |
-
"eval_samples_per_second": 12859.991,
|
| 1929 |
-
"eval_steps_per_second": 6.302,
|
| 1930 |
-
"step": 12800
|
| 1931 |
-
},
|
| 1932 |
-
{
|
| 1933 |
-
"epoch": 55.60344827586207,
|
| 1934 |
-
"grad_norm": 0.19057317078113556,
|
| 1935 |
-
"learning_rate": 0.0008316223343154266,
|
| 1936 |
-
"loss": 0.9708,
|
| 1937 |
-
"step": 12900
|
| 1938 |
-
},
|
| 1939 |
-
{
|
| 1940 |
-
"epoch": 55.60344827586207,
|
| 1941 |
-
"eval_loss": 5.028558731079102,
|
| 1942 |
-
"eval_runtime": 9.3777,
|
| 1943 |
-
"eval_samples_per_second": 12620.494,
|
| 1944 |
-
"eval_steps_per_second": 6.185,
|
| 1945 |
-
"step": 12900
|
| 1946 |
-
},
|
| 1947 |
-
{
|
| 1948 |
-
"epoch": 56.03448275862069,
|
| 1949 |
-
"grad_norm": 0.18864724040031433,
|
| 1950 |
-
"learning_rate": 0.0008182325233767267,
|
| 1951 |
-
"loss": 0.9854,
|
| 1952 |
-
"step": 13000
|
| 1953 |
-
},
|
| 1954 |
-
{
|
| 1955 |
-
"epoch": 56.03448275862069,
|
| 1956 |
-
"eval_loss": 5.237986087799072,
|
| 1957 |
-
"eval_runtime": 9.2752,
|
| 1958 |
-
"eval_samples_per_second": 12759.99,
|
| 1959 |
-
"eval_steps_per_second": 6.253,
|
| 1960 |
-
"step": 13000
|
| 1961 |
-
},
|
| 1962 |
-
{
|
| 1963 |
-
"epoch": 56.46551724137931,
|
| 1964 |
-
"grad_norm": 0.19948884844779968,
|
| 1965 |
-
"learning_rate": 0.0008048763314750851,
|
| 1966 |
-
"loss": 0.9562,
|
| 1967 |
-
"step": 13100
|
| 1968 |
-
},
|
| 1969 |
-
{
|
| 1970 |
-
"epoch": 56.46551724137931,
|
| 1971 |
-
"eval_loss": 5.091177940368652,
|
| 1972 |
-
"eval_runtime": 9.5374,
|
| 1973 |
-
"eval_samples_per_second": 12409.191,
|
| 1974 |
-
"eval_steps_per_second": 6.081,
|
| 1975 |
-
"step": 13100
|
| 1976 |
-
},
|
| 1977 |
-
{
|
| 1978 |
-
"epoch": 56.89655172413793,
|
| 1979 |
-
"grad_norm": 0.1820322722196579,
|
| 1980 |
-
"learning_rate": 0.0007915562289221262,
|
| 1981 |
-
"loss": 0.9795,
|
| 1982 |
-
"step": 13200
|
| 1983 |
-
},
|
| 1984 |
-
{
|
| 1985 |
-
"epoch": 56.89655172413793,
|
| 1986 |
-
"eval_loss": 5.0259809494018555,
|
| 1987 |
-
"eval_runtime": 9.2875,
|
| 1988 |
-
"eval_samples_per_second": 12743.094,
|
| 1989 |
-
"eval_steps_per_second": 6.245,
|
| 1990 |
-
"step": 13200
|
| 1991 |
-
},
|
| 1992 |
-
{
|
| 1993 |
-
"epoch": 57.327586206896555,
|
| 1994 |
-
"grad_norm": 0.18932276964187622,
|
| 1995 |
-
"learning_rate": 0.0007782746793545225,
|
| 1996 |
-
"loss": 0.9556,
|
| 1997 |
-
"step": 13300
|
| 1998 |
-
},
|
| 1999 |
-
{
|
| 2000 |
-
"epoch": 57.327586206896555,
|
| 2001 |
-
"eval_loss": 5.16719388961792,
|
| 2002 |
-
"eval_runtime": 9.2252,
|
| 2003 |
-
"eval_samples_per_second": 12829.131,
|
| 2004 |
-
"eval_steps_per_second": 6.287,
|
| 2005 |
-
"step": 13300
|
| 2006 |
-
},
|
| 2007 |
-
{
|
| 2008 |
-
"epoch": 57.758620689655174,
|
| 2009 |
-
"grad_norm": 0.18779167532920837,
|
| 2010 |
-
"learning_rate": 0.0007650341392783306,
|
| 2011 |
-
"loss": 0.9689,
|
| 2012 |
-
"step": 13400
|
| 2013 |
-
},
|
| 2014 |
-
{
|
| 2015 |
-
"epoch": 57.758620689655174,
|
| 2016 |
-
"eval_loss": 5.090976715087891,
|
| 2017 |
-
"eval_runtime": 9.3802,
|
| 2018 |
-
"eval_samples_per_second": 12617.111,
|
| 2019 |
-
"eval_steps_per_second": 6.183,
|
| 2020 |
-
"step": 13400
|
| 2021 |
-
},
|
| 2022 |
-
{
|
| 2023 |
-
"epoch": 58.189655172413794,
|
| 2024 |
-
"grad_norm": 0.1727251261472702,
|
| 2025 |
-
"learning_rate": 0.0007518370576146431,
|
| 2026 |
-
"loss": 0.9599,
|
| 2027 |
-
"step": 13500
|
| 2028 |
-
},
|
| 2029 |
-
{
|
| 2030 |
-
"epoch": 58.189655172413794,
|
| 2031 |
-
"eval_loss": 5.20599889755249,
|
| 2032 |
-
"eval_runtime": 9.2626,
|
| 2033 |
-
"eval_samples_per_second": 12777.352,
|
| 2034 |
-
"eval_steps_per_second": 6.262,
|
| 2035 |
-
"step": 13500
|
| 2036 |
-
},
|
| 2037 |
-
{
|
| 2038 |
-
"epoch": 58.62068965517241,
|
| 2039 |
-
"grad_norm": 0.18696245551109314,
|
| 2040 |
-
"learning_rate": 0.0007386858752466458,
|
| 2041 |
-
"loss": 0.9559,
|
| 2042 |
-
"step": 13600
|
| 2043 |
-
},
|
| 2044 |
-
{
|
| 2045 |
-
"epoch": 58.62068965517241,
|
| 2046 |
-
"eval_loss": 5.134738445281982,
|
| 2047 |
-
"eval_runtime": 9.3926,
|
| 2048 |
-
"eval_samples_per_second": 12600.491,
|
| 2049 |
-
"eval_steps_per_second": 6.175,
|
| 2050 |
-
"step": 13600
|
| 2051 |
-
},
|
| 2052 |
-
{
|
| 2053 |
-
"epoch": 59.05172413793103,
|
| 2054 |
-
"grad_norm": 0.19362613558769226,
|
| 2055 |
-
"learning_rate": 0.0007255830245681625,
|
| 2056 |
-
"loss": 0.9677,
|
| 2057 |
-
"step": 13700
|
| 2058 |
-
},
|
| 2059 |
-
{
|
| 2060 |
-
"epoch": 59.05172413793103,
|
| 2061 |
-
"eval_loss": 5.218345642089844,
|
| 2062 |
-
"eval_runtime": 9.2309,
|
| 2063 |
-
"eval_samples_per_second": 12821.143,
|
| 2064 |
-
"eval_steps_per_second": 6.283,
|
| 2065 |
-
"step": 13700
|
| 2066 |
-
},
|
| 2067 |
-
{
|
| 2068 |
-
"epoch": 59.48275862068966,
|
| 2069 |
-
"grad_norm": 0.17938446998596191,
|
| 2070 |
-
"learning_rate": 0.0007125309290337666,
|
| 2071 |
-
"loss": 0.9431,
|
| 2072 |
-
"step": 13800
|
| 2073 |
-
},
|
| 2074 |
-
{
|
| 2075 |
-
"epoch": 59.48275862068966,
|
| 2076 |
-
"eval_loss": 5.174517631530762,
|
| 2077 |
-
"eval_runtime": 9.4671,
|
| 2078 |
-
"eval_samples_per_second": 12501.228,
|
| 2079 |
-
"eval_steps_per_second": 6.126,
|
| 2080 |
-
"step": 13800
|
| 2081 |
-
},
|
| 2082 |
-
{
|
| 2083 |
-
"epoch": 59.91379310344828,
|
| 2084 |
-
"grad_norm": 0.17371727526187897,
|
| 2085 |
-
"learning_rate": 0.000699532002710548,
|
| 2086 |
-
"loss": 0.9641,
|
| 2087 |
-
"step": 13900
|
| 2088 |
-
},
|
| 2089 |
-
{
|
| 2090 |
-
"epoch": 59.91379310344828,
|
| 2091 |
-
"eval_loss": 5.125094890594482,
|
| 2092 |
-
"eval_runtime": 9.3495,
|
| 2093 |
-
"eval_samples_per_second": 12658.593,
|
| 2094 |
-
"eval_steps_per_second": 6.204,
|
| 2095 |
-
"step": 13900
|
| 2096 |
-
},
|
| 2097 |
-
{
|
| 2098 |
-
"epoch": 60.3448275862069,
|
| 2099 |
-
"grad_norm": 0.1803039014339447,
|
| 2100 |
-
"learning_rate": 0.0006865886498316185,
|
| 2101 |
-
"loss": 0.9402,
|
| 2102 |
-
"step": 14000
|
| 2103 |
-
},
|
| 2104 |
-
{
|
| 2105 |
-
"epoch": 60.3448275862069,
|
| 2106 |
-
"eval_loss": 5.229825496673584,
|
| 2107 |
-
"eval_runtime": 9.2198,
|
| 2108 |
-
"eval_samples_per_second": 12836.561,
|
| 2109 |
-
"eval_steps_per_second": 6.291,
|
| 2110 |
-
"step": 14000
|
| 2111 |
-
},
|
| 2112 |
-
{
|
| 2113 |
-
"epoch": 60.775862068965516,
|
| 2114 |
-
"grad_norm": 0.17432528734207153,
|
| 2115 |
-
"learning_rate": 0.0006737032643514306,
|
| 2116 |
-
"loss": 0.9542,
|
| 2117 |
-
"step": 14100
|
| 2118 |
-
},
|
| 2119 |
-
{
|
| 2120 |
-
"epoch": 60.775862068965516,
|
| 2121 |
-
"eval_loss": 5.173377513885498,
|
| 2122 |
-
"eval_runtime": 9.6205,
|
| 2123 |
-
"eval_samples_per_second": 12301.935,
|
| 2124 |
-
"eval_steps_per_second": 6.029,
|
| 2125 |
-
"step": 14100
|
| 2126 |
-
},
|
| 2127 |
-
{
|
| 2128 |
-
"epoch": 61.206896551724135,
|
| 2129 |
-
"grad_norm": 0.17738671600818634,
|
| 2130 |
-
"learning_rate": 0.000660878229503003,
|
| 2131 |
-
"loss": 0.9459,
|
| 2132 |
-
"step": 14200
|
| 2133 |
-
},
|
| 2134 |
-
{
|
| 2135 |
-
"epoch": 61.206896551724135,
|
| 2136 |
-
"eval_loss": 5.284204006195068,
|
| 2137 |
-
"eval_runtime": 9.202,
|
| 2138 |
-
"eval_samples_per_second": 12861.408,
|
| 2139 |
-
"eval_steps_per_second": 6.303,
|
| 2140 |
-
"step": 14200
|
| 2141 |
-
},
|
| 2142 |
-
{
|
| 2143 |
-
"epoch": 61.63793103448276,
|
| 2144 |
-
"grad_norm": 0.17412865161895752,
|
| 2145 |
-
"learning_rate": 0.0006481159173571249,
|
| 2146 |
-
"loss": 0.9431,
|
| 2147 |
-
"step": 14300
|
| 2148 |
-
},
|
| 2149 |
-
{
|
| 2150 |
-
"epoch": 61.63793103448276,
|
| 2151 |
-
"eval_loss": 5.202380180358887,
|
| 2152 |
-
"eval_runtime": 9.2023,
|
| 2153 |
-
"eval_samples_per_second": 12861.037,
|
| 2154 |
-
"eval_steps_per_second": 6.303,
|
| 2155 |
-
"step": 14300
|
| 2156 |
-
},
|
| 2157 |
-
{
|
| 2158 |
-
"epoch": 62.06896551724138,
|
| 2159 |
-
"grad_norm": 0.1586960405111313,
|
| 2160 |
-
"learning_rate": 0.0006354186883836291,
|
| 2161 |
-
"loss": 0.951,
|
| 2162 |
-
"step": 14400
|
| 2163 |
-
},
|
| 2164 |
-
{
|
| 2165 |
-
"epoch": 62.06896551724138,
|
| 2166 |
-
"eval_loss": 5.338278293609619,
|
| 2167 |
-
"eval_runtime": 9.3841,
|
| 2168 |
-
"eval_samples_per_second": 12611.844,
|
| 2169 |
-
"eval_steps_per_second": 6.181,
|
| 2170 |
-
"step": 14400
|
| 2171 |
-
},
|
| 2172 |
-
{
|
| 2173 |
-
"epoch": 62.5,
|
| 2174 |
-
"grad_norm": 0.16516196727752686,
|
| 2175 |
-
"learning_rate": 0.0006227888910148052,
|
| 2176 |
-
"loss": 0.9316,
|
| 2177 |
-
"step": 14500
|
| 2178 |
-
},
|
| 2179 |
-
{
|
| 2180 |
-
"epoch": 62.5,
|
| 2181 |
-
"eval_loss": 5.300503253936768,
|
| 2182 |
-
"eval_runtime": 9.3048,
|
| 2183 |
-
"eval_samples_per_second": 12719.348,
|
| 2184 |
-
"eval_steps_per_second": 6.233,
|
| 2185 |
-
"step": 14500
|
| 2186 |
-
},
|
| 2187 |
-
{
|
| 2188 |
-
"epoch": 62.93103448275862,
|
| 2189 |
-
"grad_norm": 0.17453870177268982,
|
| 2190 |
-
"learning_rate": 0.000610228861211044,
|
| 2191 |
-
"loss": 0.9506,
|
| 2192 |
-
"step": 14600
|
| 2193 |
-
},
|
| 2194 |
-
{
|
| 2195 |
-
"epoch": 62.93103448275862,
|
| 2196 |
-
"eval_loss": 5.2108259201049805,
|
| 2197 |
-
"eval_runtime": 9.373,
|
| 2198 |
-
"eval_samples_per_second": 12626.747,
|
| 2199 |
-
"eval_steps_per_second": 6.188,
|
| 2200 |
-
"step": 14600
|
| 2201 |
-
},
|
| 2202 |
-
{
|
| 2203 |
-
"epoch": 63.36206896551724,
|
| 2204 |
-
"grad_norm": 0.18113704025745392,
|
| 2205 |
-
"learning_rate": 0.0005977409220287874,
|
| 2206 |
-
"loss": 0.9268,
|
| 2207 |
-
"step": 14700
|
| 2208 |
-
},
|
| 2209 |
-
{
|
| 2210 |
-
"epoch": 63.36206896551724,
|
| 2211 |
-
"eval_loss": 5.307285785675049,
|
| 2212 |
-
"eval_runtime": 9.2153,
|
| 2213 |
-
"eval_samples_per_second": 12842.815,
|
| 2214 |
-
"eval_steps_per_second": 6.294,
|
| 2215 |
-
"step": 14700
|
| 2216 |
-
},
|
| 2217 |
-
{
|
| 2218 |
-
"epoch": 63.793103448275865,
|
| 2219 |
-
"grad_norm": 0.16791464388370514,
|
| 2220 |
-
"learning_rate": 0.0005853273831908637,
|
| 2221 |
-
"loss": 0.941,
|
| 2222 |
-
"step": 14800
|
| 2223 |
-
},
|
| 2224 |
-
{
|
| 2225 |
-
"epoch": 63.793103448275865,
|
| 2226 |
-
"eval_loss": 5.276530742645264,
|
| 2227 |
-
"eval_runtime": 9.3621,
|
| 2228 |
-
"eval_samples_per_second": 12641.481,
|
| 2229 |
-
"eval_steps_per_second": 6.195,
|
| 2230 |
-
"step": 14800
|
| 2231 |
-
},
|
| 2232 |
-
{
|
| 2233 |
-
"epoch": 64.22413793103448,
|
| 2234 |
-
"grad_norm": 0.18001683056354523,
|
| 2235 |
-
"learning_rate": 0.0005729905406592884,
|
| 2236 |
-
"loss": 0.9315,
|
| 2237 |
-
"step": 14900
|
| 2238 |
-
},
|
| 2239 |
-
{
|
| 2240 |
-
"epoch": 64.22413793103448,
|
| 2241 |
-
"eval_loss": 5.365150451660156,
|
| 2242 |
-
"eval_runtime": 9.3887,
|
| 2243 |
-
"eval_samples_per_second": 12605.671,
|
| 2244 |
-
"eval_steps_per_second": 6.178,
|
| 2245 |
-
"step": 14900
|
| 2246 |
-
},
|
| 2247 |
-
{
|
| 2248 |
-
"epoch": 64.65517241379311,
|
| 2249 |
-
"grad_norm": 0.1623552292585373,
|
| 2250 |
-
"learning_rate": 0.0005607326762106162,
|
| 2251 |
-
"loss": 0.9308,
|
| 2252 |
-
"step": 15000
|
| 2253 |
-
},
|
| 2254 |
-
{
|
| 2255 |
-
"epoch": 64.65517241379311,
|
| 2256 |
-
"eval_loss": 5.266965389251709,
|
| 2257 |
-
"eval_runtime": 9.2811,
|
| 2258 |
-
"eval_samples_per_second": 12751.873,
|
| 2259 |
-
"eval_steps_per_second": 6.249,
|
| 2260 |
-
"step": 15000
|
| 2261 |
-
},
|
| 2262 |
-
{
|
| 2263 |
-
"epoch": 65.08620689655173,
|
| 2264 |
-
"grad_norm": 0.16720953583717346,
|
| 2265 |
-
"learning_rate": 0.0005485560570139061,
|
| 2266 |
-
"loss": 0.9359,
|
| 2267 |
-
"step": 15100
|
| 2268 |
-
},
|
| 2269 |
-
{
|
| 2270 |
-
"epoch": 65.08620689655173,
|
| 2271 |
-
"eval_loss": 5.438762664794922,
|
| 2272 |
-
"eval_runtime": 9.4208,
|
| 2273 |
-
"eval_samples_per_second": 12562.678,
|
| 2274 |
-
"eval_steps_per_second": 6.157,
|
| 2275 |
-
"step": 15100
|
| 2276 |
-
},
|
| 2277 |
-
{
|
| 2278 |
-
"epoch": 65.51724137931035,
|
| 2279 |
-
"grad_norm": 0.1636320948600769,
|
| 2280 |
-
"learning_rate": 0.0005364629352113988,
|
| 2281 |
-
"loss": 0.9214,
|
| 2282 |
-
"step": 15200
|
| 2283 |
-
},
|
| 2284 |
-
{
|
| 2285 |
-
"epoch": 65.51724137931035,
|
| 2286 |
-
"eval_loss": 5.348054885864258,
|
| 2287 |
-
"eval_runtime": 9.2475,
|
| 2288 |
-
"eval_samples_per_second": 12798.204,
|
| 2289 |
-
"eval_steps_per_second": 6.272,
|
| 2290 |
-
"step": 15200
|
| 2291 |
-
},
|
| 2292 |
-
{
|
| 2293 |
-
"epoch": 65.94827586206897,
|
| 2294 |
-
"grad_norm": 0.1635085791349411,
|
| 2295 |
-
"learning_rate": 0.0005244555475019666,
|
| 2296 |
-
"loss": 0.9376,
|
| 2297 |
-
"step": 15300
|
| 2298 |
-
},
|
| 2299 |
-
{
|
| 2300 |
-
"epoch": 65.94827586206897,
|
| 2301 |
-
"eval_loss": 5.3104448318481445,
|
| 2302 |
-
"eval_runtime": 9.394,
|
| 2303 |
-
"eval_samples_per_second": 12598.626,
|
| 2304 |
-
"eval_steps_per_second": 6.174,
|
| 2305 |
-
"step": 15300
|
| 2306 |
-
},
|
| 2307 |
-
{
|
| 2308 |
-
"epoch": 66.37931034482759,
|
| 2309 |
-
"grad_norm": 0.15515539050102234,
|
| 2310 |
-
"learning_rate": 0.000512536114727423,
|
| 2311 |
-
"loss": 0.914,
|
| 2312 |
-
"step": 15400
|
| 2313 |
-
},
|
| 2314 |
-
{
|
| 2315 |
-
"epoch": 66.37931034482759,
|
| 2316 |
-
"eval_loss": 5.391454696655273,
|
| 2317 |
-
"eval_runtime": 9.4016,
|
| 2318 |
-
"eval_samples_per_second": 12588.456,
|
| 2319 |
-
"eval_steps_per_second": 6.169,
|
| 2320 |
-
"step": 15400
|
| 2321 |
-
},
|
| 2322 |
-
{
|
| 2323 |
-
"epoch": 66.8103448275862,
|
| 2324 |
-
"grad_norm": 0.15986432135105133,
|
| 2325 |
-
"learning_rate": 0.0005007068414617632,
|
| 2326 |
-
"loss": 0.9296,
|
| 2327 |
-
"step": 15500
|
| 2328 |
-
},
|
| 2329 |
-
{
|
| 2330 |
-
"epoch": 66.8103448275862,
|
| 2331 |
-
"eval_loss": 5.335239887237549,
|
| 2332 |
-
"eval_runtime": 9.2358,
|
| 2333 |
-
"eval_samples_per_second": 12814.357,
|
| 2334 |
-
"eval_steps_per_second": 6.28,
|
| 2335 |
-
"step": 15500
|
| 2336 |
-
},
|
| 2337 |
-
{
|
| 2338 |
-
"epoch": 67.24137931034483,
|
| 2339 |
-
"grad_norm": 0.15565365552902222,
|
| 2340 |
-
"learning_rate": 0.0004889699156034146,
|
| 2341 |
-
"loss": 0.9188,
|
| 2342 |
-
"step": 15600
|
| 2343 |
-
},
|
| 2344 |
-
{
|
| 2345 |
-
"epoch": 67.24137931034483,
|
| 2346 |
-
"eval_loss": 5.442201137542725,
|
| 2347 |
-
"eval_runtime": 9.493,
|
| 2348 |
-
"eval_samples_per_second": 12467.232,
|
| 2349 |
-
"eval_steps_per_second": 6.11,
|
| 2350 |
-
"step": 15600
|
| 2351 |
-
},
|
| 2352 |
-
{
|
| 2353 |
-
"epoch": 67.67241379310344,
|
| 2354 |
-
"grad_norm": 0.160415917634964,
|
| 2355 |
-
"learning_rate": 0.0004773275079705718,
|
| 2356 |
-
"loss": 0.9198,
|
| 2357 |
-
"step": 15700
|
| 2358 |
-
},
|
| 2359 |
-
{
|
| 2360 |
-
"epoch": 67.67241379310344,
|
| 2361 |
-
"eval_loss": 5.36320686340332,
|
| 2362 |
-
"eval_runtime": 9.1953,
|
| 2363 |
-
"eval_samples_per_second": 12870.809,
|
| 2364 |
-
"eval_steps_per_second": 6.308,
|
| 2365 |
-
"step": 15700
|
| 2366 |
-
},
|
| 2367 |
-
{
|
| 2368 |
-
"epoch": 68.10344827586206,
|
| 2369 |
-
"grad_norm": 0.17050059139728546,
|
| 2370 |
-
"learning_rate": 0.00046578177189968904,
|
| 2371 |
-
"loss": 0.923,
|
| 2372 |
-
"step": 15800
|
| 2373 |
-
},
|
| 2374 |
-
{
|
| 2375 |
-
"epoch": 68.10344827586206,
|
| 2376 |
-
"eval_loss": 5.504161357879639,
|
| 2377 |
-
"eval_runtime": 9.194,
|
| 2378 |
-
"eval_samples_per_second": 12872.672,
|
| 2379 |
-
"eval_steps_per_second": 6.308,
|
| 2380 |
-
"step": 15800
|
| 2381 |
-
},
|
| 2382 |
-
{
|
| 2383 |
-
"epoch": 68.53448275862068,
|
| 2384 |
-
"grad_norm": 0.14325299859046936,
|
| 2385 |
-
"learning_rate": 0.0004543348428472082,
|
| 2386 |
-
"loss": 0.9104,
|
| 2387 |
-
"step": 15900
|
| 2388 |
-
},
|
| 2389 |
-
{
|
| 2390 |
-
"epoch": 68.53448275862068,
|
| 2391 |
-
"eval_loss": 5.397451877593994,
|
| 2392 |
-
"eval_runtime": 9.3626,
|
| 2393 |
-
"eval_samples_per_second": 12640.857,
|
| 2394 |
-
"eval_steps_per_second": 6.195,
|
| 2395 |
-
"step": 15900
|
| 2396 |
-
},
|
| 2397 |
-
{
|
| 2398 |
-
"epoch": 68.96551724137932,
|
| 2399 |
-
"grad_norm": 0.1505531370639801,
|
| 2400 |
-
"learning_rate": 0.0004429888379945914,
|
| 2401 |
-
"loss": 0.9259,
|
| 2402 |
-
"step": 16000
|
| 2403 |
-
},
|
| 2404 |
-
{
|
| 2405 |
-
"epoch": 68.96551724137932,
|
| 2406 |
-
"eval_loss": 5.372323036193848,
|
| 2407 |
-
"eval_runtime": 9.2765,
|
| 2408 |
-
"eval_samples_per_second": 12758.16,
|
| 2409 |
-
"eval_steps_per_second": 6.252,
|
| 2410 |
-
"step": 16000
|
| 2411 |
-
},
|
| 2412 |
-
{
|
| 2413 |
-
"epoch": 69.39655172413794,
|
| 2414 |
-
"grad_norm": 0.14758853614330292,
|
| 2415 |
-
"learning_rate": 0.00043174585585673675,
|
| 2416 |
-
"loss": 0.9034,
|
| 2417 |
-
"step": 16100
|
| 2418 |
-
},
|
| 2419 |
-
{
|
| 2420 |
-
"epoch": 69.39655172413794,
|
| 2421 |
-
"eval_loss": 5.451719284057617,
|
| 2422 |
-
"eval_runtime": 9.5225,
|
| 2423 |
-
"eval_samples_per_second": 12428.515,
|
| 2424 |
-
"eval_steps_per_second": 6.091,
|
| 2425 |
-
"step": 16100
|
| 2426 |
-
},
|
| 2427 |
-
{
|
| 2428 |
-
"epoch": 69.82758620689656,
|
| 2429 |
-
"grad_norm": 0.16002579033374786,
|
| 2430 |
-
"learning_rate": 0.00042060797589384325,
|
| 2431 |
-
"loss": 0.9185,
|
| 2432 |
-
"step": 16200
|
| 2433 |
-
},
|
| 2434 |
-
{
|
| 2435 |
-
"epoch": 69.82758620689656,
|
| 2436 |
-
"eval_loss": 5.384088516235352,
|
| 2437 |
-
"eval_runtime": 9.2516,
|
| 2438 |
-
"eval_samples_per_second": 12792.54,
|
| 2439 |
-
"eval_steps_per_second": 6.269,
|
| 2440 |
-
"step": 16200
|
| 2441 |
-
},
|
| 2442 |
-
{
|
| 2443 |
-
"epoch": 70.25862068965517,
|
| 2444 |
-
"grad_norm": 0.15093061327934265,
|
| 2445 |
-
"learning_rate": 0.00040957725812680227,
|
| 2446 |
-
"loss": 0.9071,
|
| 2447 |
-
"step": 16300
|
| 2448 |
-
},
|
| 2449 |
-
{
|
| 2450 |
-
"epoch": 70.25862068965517,
|
| 2451 |
-
"eval_loss": 5.495941638946533,
|
| 2452 |
-
"eval_runtime": 9.2246,
|
| 2453 |
-
"eval_samples_per_second": 12829.882,
|
| 2454 |
-
"eval_steps_per_second": 6.288,
|
| 2455 |
-
"step": 16300
|
| 2456 |
-
},
|
| 2457 |
-
{
|
| 2458 |
-
"epoch": 70.6896551724138,
|
| 2459 |
-
"grad_norm": 0.14055319130420685,
|
| 2460 |
-
"learning_rate": 0.00039865574275618353,
|
| 2461 |
-
"loss": 0.9105,
|
| 2462 |
-
"step": 16400
|
| 2463 |
-
},
|
| 2464 |
-
{
|
| 2465 |
-
"epoch": 70.6896551724138,
|
| 2466 |
-
"eval_loss": 5.418017864227295,
|
| 2467 |
-
"eval_runtime": 9.3637,
|
| 2468 |
-
"eval_samples_per_second": 12639.396,
|
| 2469 |
-
"eval_steps_per_second": 6.194,
|
| 2470 |
-
"step": 16400
|
| 2471 |
-
},
|
| 2472 |
-
{
|
| 2473 |
-
"epoch": 71.12068965517241,
|
| 2474 |
-
"grad_norm": 0.1445504128932953,
|
| 2475 |
-
"learning_rate": 0.00038784544978488756,
|
| 2476 |
-
"loss": 0.9127,
|
| 2477 |
-
"step": 16500
|
| 2478 |
-
},
|
| 2479 |
-
{
|
| 2480 |
-
"epoch": 71.12068965517241,
|
| 2481 |
-
"eval_loss": 5.526876449584961,
|
| 2482 |
-
"eval_runtime": 9.2747,
|
| 2483 |
-
"eval_samples_per_second": 12760.573,
|
| 2484 |
-
"eval_steps_per_second": 6.254,
|
| 2485 |
-
"step": 16500
|
| 2486 |
-
},
|
| 2487 |
-
{
|
| 2488 |
-
"epoch": 71.55172413793103,
|
| 2489 |
-
"grad_norm": 0.14889004826545715,
|
| 2490 |
-
"learning_rate": 0.0003771483786445331,
|
| 2491 |
-
"loss": 0.903,
|
| 2492 |
-
"step": 16600
|
| 2493 |
-
},
|
| 2494 |
-
{
|
| 2495 |
-
"epoch": 71.55172413793103,
|
| 2496 |
-
"eval_loss": 5.482020854949951,
|
| 2497 |
-
"eval_runtime": 9.5332,
|
| 2498 |
-
"eval_samples_per_second": 12414.639,
|
| 2499 |
-
"eval_steps_per_second": 6.084,
|
| 2500 |
-
"step": 16600
|
| 2501 |
-
},
|
| 2502 |
-
{
|
| 2503 |
-
"epoch": 71.98275862068965,
|
| 2504 |
-
"grad_norm": 0.14940929412841797,
|
| 2505 |
-
"learning_rate": 0.00036656650782564983,
|
| 2506 |
-
"loss": 0.9144,
|
| 2507 |
-
"step": 16700
|
| 2508 |
-
},
|
| 2509 |
-
{
|
| 2510 |
-
"epoch": 71.98275862068965,
|
| 2511 |
-
"eval_loss": 5.4448442459106445,
|
| 2512 |
-
"eval_runtime": 9.2742,
|
| 2513 |
-
"eval_samples_per_second": 12761.28,
|
| 2514 |
-
"eval_steps_per_second": 6.254,
|
| 2515 |
-
"step": 16700
|
| 2516 |
-
},
|
| 2517 |
-
{
|
| 2518 |
-
"epoch": 72.41379310344827,
|
| 2519 |
-
"grad_norm": 0.14626102149486542,
|
| 2520 |
-
"learning_rate": 0.00035610179451174307,
|
| 2521 |
-
"loss": 0.8945,
|
| 2522 |
-
"step": 16800
|
| 2523 |
-
},
|
| 2524 |
-
{
|
| 2525 |
-
"epoch": 72.41379310344827,
|
| 2526 |
-
"eval_loss": 5.535341739654541,
|
| 2527 |
-
"eval_runtime": 9.2018,
|
| 2528 |
-
"eval_samples_per_second": 12861.765,
|
| 2529 |
-
"eval_steps_per_second": 6.303,
|
| 2530 |
-
"step": 16800
|
| 2531 |
-
},
|
| 2532 |
-
{
|
| 2533 |
-
"epoch": 72.84482758620689,
|
| 2534 |
-
"grad_norm": 0.14408394694328308,
|
| 2535 |
-
"learning_rate": 0.0003457561742173032,
|
| 2536 |
-
"loss": 0.9088,
|
| 2537 |
-
"step": 16900
|
| 2538 |
-
},
|
| 2539 |
-
{
|
| 2540 |
-
"epoch": 72.84482758620689,
|
| 2541 |
-
"eval_loss": 5.446293354034424,
|
| 2542 |
-
"eval_runtime": 9.3364,
|
| 2543 |
-
"eval_samples_per_second": 12676.282,
|
| 2544 |
-
"eval_steps_per_second": 6.212,
|
| 2545 |
-
"step": 16900
|
| 2546 |
-
},
|
| 2547 |
-
{
|
| 2548 |
-
"epoch": 73.27586206896552,
|
| 2549 |
-
"grad_norm": 0.14265799522399902,
|
| 2550 |
-
"learning_rate": 0.00033553156042981716,
|
| 2551 |
-
"loss": 0.8975,
|
| 2552 |
-
"step": 17000
|
| 2553 |
-
},
|
| 2554 |
-
{
|
| 2555 |
-
"epoch": 73.27586206896552,
|
| 2556 |
-
"eval_loss": 5.535012722015381,
|
| 2557 |
-
"eval_runtime": 9.2156,
|
| 2558 |
-
"eval_samples_per_second": 12842.519,
|
| 2559 |
-
"eval_steps_per_second": 6.294,
|
| 2560 |
-
"step": 17000
|
| 2561 |
-
},
|
| 2562 |
-
{
|
| 2563 |
-
"epoch": 73.70689655172414,
|
| 2564 |
-
"grad_norm": 0.146506205201149,
|
| 2565 |
-
"learning_rate": 0.0003254298442558571,
|
| 2566 |
-
"loss": 0.9019,
|
| 2567 |
-
"step": 17100
|
| 2568 |
-
},
|
| 2569 |
-
{
|
| 2570 |
-
"epoch": 73.70689655172414,
|
| 2571 |
-
"eval_loss": 5.51116418838501,
|
| 2572 |
-
"eval_runtime": 9.3669,
|
| 2573 |
-
"eval_samples_per_second": 12635.03,
|
| 2574 |
-
"eval_steps_per_second": 6.192,
|
| 2575 |
-
"step": 17100
|
| 2576 |
-
},
|
| 2577 |
-
{
|
| 2578 |
-
"epoch": 74.13793103448276,
|
| 2579 |
-
"grad_norm": 0.14774905145168304,
|
| 2580 |
-
"learning_rate": 0.00031545289407131126,
|
| 2581 |
-
"loss": 0.9005,
|
| 2582 |
-
"step": 17200
|
| 2583 |
-
},
|
| 2584 |
-
{
|
| 2585 |
-
"epoch": 74.13793103448276,
|
| 2586 |
-
"eval_loss": 5.60396671295166,
|
| 2587 |
-
"eval_runtime": 9.252,
|
| 2588 |
-
"eval_samples_per_second": 12791.945,
|
| 2589 |
-
"eval_steps_per_second": 6.269,
|
| 2590 |
-
"step": 17200
|
| 2591 |
-
},
|
| 2592 |
-
{
|
| 2593 |
-
"epoch": 74.56896551724138,
|
| 2594 |
-
"grad_norm": 0.15397560596466064,
|
| 2595 |
-
"learning_rate": 0.000305602555175813,
|
| 2596 |
-
"loss": 0.8947,
|
| 2597 |
-
"step": 17300
|
| 2598 |
-
},
|
| 2599 |
-
{
|
| 2600 |
-
"epoch": 74.56896551724138,
|
| 2601 |
-
"eval_loss": 5.518400192260742,
|
| 2602 |
-
"eval_runtime": 9.2957,
|
| 2603 |
-
"eval_samples_per_second": 12731.779,
|
| 2604 |
-
"eval_steps_per_second": 6.239,
|
| 2605 |
-
"step": 17300
|
| 2606 |
-
},
|
| 2607 |
-
{
|
| 2608 |
-
"epoch": 75.0,
|
| 2609 |
-
"grad_norm": 0.14761576056480408,
|
| 2610 |
-
"learning_rate": 0.00029588064945144135,
|
| 2611 |
-
"loss": 0.9052,
|
| 2612 |
-
"step": 17400
|
| 2613 |
-
},
|
| 2614 |
-
{
|
| 2615 |
-
"epoch": 75.0,
|
| 2616 |
-
"eval_loss": 5.501093864440918,
|
| 2617 |
-
"eval_runtime": 9.4777,
|
| 2618 |
-
"eval_samples_per_second": 12487.311,
|
| 2619 |
-
"eval_steps_per_second": 6.12,
|
| 2620 |
-
"step": 17400
|
| 2621 |
-
},
|
| 2622 |
-
{
|
| 2623 |
-
"epoch": 75.43103448275862,
|
| 2624 |
-
"grad_norm": 0.14727619290351868,
|
| 2625 |
-
"learning_rate": 0.0002862889750257551,
|
| 2626 |
-
"loss": 0.8863,
|
| 2627 |
-
"step": 17500
|
| 2628 |
-
},
|
| 2629 |
-
{
|
| 2630 |
-
"epoch": 75.43103448275862,
|
| 2631 |
-
"eval_loss": 5.560401916503906,
|
| 2632 |
-
"eval_runtime": 9.1883,
|
| 2633 |
-
"eval_samples_per_second": 12880.563,
|
| 2634 |
-
"eval_steps_per_second": 6.312,
|
| 2635 |
-
"step": 17500
|
| 2636 |
-
},
|
| 2637 |
-
{
|
| 2638 |
-
"epoch": 75.86206896551724,
|
| 2639 |
-
"grad_norm": 0.15626391768455505,
|
| 2640 |
-
"learning_rate": 0.0002768293059392143,
|
| 2641 |
-
"loss": 0.8993,
|
| 2642 |
-
"step": 17600
|
| 2643 |
-
},
|
| 2644 |
-
{
|
| 2645 |
-
"epoch": 75.86206896551724,
|
| 2646 |
-
"eval_loss": 5.520768642425537,
|
| 2647 |
-
"eval_runtime": 9.1909,
|
| 2648 |
-
"eval_samples_per_second": 12876.988,
|
| 2649 |
-
"eval_steps_per_second": 6.311,
|
| 2650 |
-
"step": 17600
|
| 2651 |
-
},
|
| 2652 |
-
{
|
| 2653 |
-
"epoch": 76.29310344827586,
|
| 2654 |
-
"grad_norm": 0.14485207200050354,
|
| 2655 |
-
"learning_rate": 0.0002675033918170623,
|
| 2656 |
-
"loss": 0.8885,
|
| 2657 |
-
"step": 17700
|
| 2658 |
-
},
|
| 2659 |
-
{
|
| 2660 |
-
"epoch": 76.29310344827586,
|
| 2661 |
-
"eval_loss": 5.576803207397461,
|
| 2662 |
-
"eval_runtime": 9.3606,
|
| 2663 |
-
"eval_samples_per_second": 12643.536,
|
| 2664 |
-
"eval_steps_per_second": 6.196,
|
| 2665 |
-
"step": 17700
|
| 2666 |
-
},
|
| 2667 |
-
{
|
| 2668 |
-
"epoch": 76.72413793103448,
|
| 2669 |
-
"grad_norm": 0.13398423790931702,
|
| 2670 |
-
"learning_rate": 0.0002583129575457227,
|
| 2671 |
-
"loss": 0.8936,
|
| 2672 |
-
"step": 17800
|
| 2673 |
-
},
|
| 2674 |
-
{
|
| 2675 |
-
"epoch": 76.72413793103448,
|
| 2676 |
-
"eval_loss": 5.554868221282959,
|
| 2677 |
-
"eval_runtime": 9.2384,
|
| 2678 |
-
"eval_samples_per_second": 12810.763,
|
| 2679 |
-
"eval_steps_per_second": 6.278,
|
| 2680 |
-
"step": 17800
|
| 2681 |
-
},
|
| 2682 |
-
{
|
| 2683 |
-
"epoch": 77.15517241379311,
|
| 2684 |
-
"grad_norm": 0.13094207644462585,
|
| 2685 |
-
"learning_rate": 0.0002492597029537672,
|
| 2686 |
-
"loss": 0.8919,
|
| 2687 |
-
"step": 17900
|
| 2688 |
-
},
|
| 2689 |
-
{
|
| 2690 |
-
"epoch": 77.15517241379311,
|
| 2691 |
-
"eval_loss": 5.611755847930908,
|
| 2692 |
-
"eval_runtime": 9.3911,
|
| 2693 |
-
"eval_samples_per_second": 12602.462,
|
| 2694 |
-
"eval_steps_per_second": 6.176,
|
| 2695 |
-
"step": 17900
|
| 2696 |
-
},
|
| 2697 |
-
{
|
| 2698 |
-
"epoch": 77.58620689655173,
|
| 2699 |
-
"grad_norm": 0.13792350888252258,
|
| 2700 |
-
"learning_rate": 0.00024034530249752463,
|
| 2701 |
-
"loss": 0.887,
|
| 2702 |
-
"step": 18000
|
| 2703 |
-
},
|
| 2704 |
-
{
|
| 2705 |
-
"epoch": 77.58620689655173,
|
| 2706 |
-
"eval_loss": 5.579117774963379,
|
| 2707 |
-
"eval_runtime": 9.36,
|
| 2708 |
-
"eval_samples_per_second": 12644.296,
|
| 2709 |
-
"eval_steps_per_second": 6.197,
|
| 2710 |
-
"step": 18000
|
| 2711 |
-
},
|
| 2712 |
-
{
|
| 2713 |
-
"epoch": 78.01724137931035,
|
| 2714 |
-
"grad_norm": 0.13721516728401184,
|
| 2715 |
-
"learning_rate": 0.00023157140495137996,
|
| 2716 |
-
"loss": 0.8951,
|
| 2717 |
-
"step": 18100
|
| 2718 |
-
},
|
| 2719 |
-
{
|
| 2720 |
-
"epoch": 78.01724137931035,
|
| 2721 |
-
"eval_loss": 5.630533695220947,
|
| 2722 |
-
"eval_runtime": 9.2429,
|
| 2723 |
-
"eval_samples_per_second": 12804.499,
|
| 2724 |
-
"eval_steps_per_second": 6.275,
|
| 2725 |
-
"step": 18100
|
| 2726 |
-
},
|
| 2727 |
-
{
|
| 2728 |
-
"epoch": 78.44827586206897,
|
| 2729 |
-
"grad_norm": 0.13419011235237122,
|
| 2730 |
-
"learning_rate": 0.00022293963310281994,
|
| 2731 |
-
"loss": 0.8804,
|
| 2732 |
-
"step": 18200
|
| 2733 |
-
},
|
| 2734 |
-
{
|
| 2735 |
-
"epoch": 78.44827586206897,
|
| 2736 |
-
"eval_loss": 5.606773853302002,
|
| 2737 |
-
"eval_runtime": 9.2669,
|
| 2738 |
-
"eval_samples_per_second": 12771.352,
|
| 2739 |
-
"eval_steps_per_second": 6.259,
|
| 2740 |
-
"step": 18200
|
| 2741 |
-
},
|
| 2742 |
-
{
|
| 2743 |
-
"epoch": 78.87931034482759,
|
| 2744 |
-
"grad_norm": 0.137063667178154,
|
| 2745 |
-
"learning_rate": 0.00021445158345229155,
|
| 2746 |
-
"loss": 0.8912,
|
| 2747 |
-
"step": 18300
|
| 2748 |
-
},
|
| 2749 |
-
{
|
| 2750 |
-
"epoch": 78.87931034482759,
|
| 2751 |
-
"eval_loss": 5.56123161315918,
|
| 2752 |
-
"eval_runtime": 9.2532,
|
| 2753 |
-
"eval_samples_per_second": 12790.212,
|
| 2754 |
-
"eval_steps_per_second": 6.268,
|
| 2755 |
-
"step": 18300
|
| 2756 |
-
},
|
| 2757 |
-
{
|
| 2758 |
-
"epoch": 79.3103448275862,
|
| 2759 |
-
"grad_norm": 0.13209742307662964,
|
| 2760 |
-
"learning_rate": 0.00020610882591791857,
|
| 2761 |
-
"loss": 0.8813,
|
| 2762 |
-
"step": 18400
|
| 2763 |
-
},
|
| 2764 |
-
{
|
| 2765 |
-
"epoch": 79.3103448275862,
|
| 2766 |
-
"eval_loss": 5.633670806884766,
|
| 2767 |
-
"eval_runtime": 9.3853,
|
| 2768 |
-
"eval_samples_per_second": 12610.295,
|
| 2769 |
-
"eval_steps_per_second": 6.18,
|
| 2770 |
-
"step": 18400
|
| 2771 |
-
},
|
| 2772 |
-
{
|
| 2773 |
-
"epoch": 79.74137931034483,
|
| 2774 |
-
"grad_norm": 0.13960996270179749,
|
| 2775 |
-
"learning_rate": 0.0001979129035451337,
|
| 2776 |
-
"loss": 0.8861,
|
| 2777 |
-
"step": 18500
|
| 2778 |
-
},
|
| 2779 |
-
{
|
| 2780 |
-
"epoch": 79.74137931034483,
|
| 2781 |
-
"eval_loss": 5.5989484786987305,
|
| 2782 |
-
"eval_runtime": 9.2688,
|
| 2783 |
-
"eval_samples_per_second": 12768.736,
|
| 2784 |
-
"eval_steps_per_second": 6.258,
|
| 2785 |
-
"step": 18500
|
| 2786 |
-
},
|
| 2787 |
-
{
|
| 2788 |
-
"epoch": 80.17241379310344,
|
| 2789 |
-
"grad_norm": 0.12470439076423645,
|
| 2790 |
-
"learning_rate": 0.0001898653322212841,
|
| 2791 |
-
"loss": 0.8838,
|
| 2792 |
-
"step": 18600
|
| 2793 |
-
},
|
| 2794 |
-
{
|
| 2795 |
-
"epoch": 80.17241379310344,
|
| 2796 |
-
"eval_loss": 5.66691780090332,
|
| 2797 |
-
"eval_runtime": 9.2463,
|
| 2798 |
-
"eval_samples_per_second": 12799.872,
|
| 2799 |
-
"eval_steps_per_second": 6.273,
|
| 2800 |
-
"step": 18600
|
| 2801 |
-
},
|
| 2802 |
-
{
|
| 2803 |
-
"epoch": 80.60344827586206,
|
| 2804 |
-
"grad_norm": 0.13329234719276428,
|
| 2805 |
-
"learning_rate": 0.00018204583118856953,
|
| 2806 |
-
"loss": 0.8798,
|
| 2807 |
-
"step": 18700
|
| 2808 |
-
},
|
| 2809 |
-
{
|
| 2810 |
-
"epoch": 80.60344827586206,
|
| 2811 |
-
"eval_loss": 5.619058132171631,
|
| 2812 |
-
"eval_runtime": 9.3773,
|
| 2813 |
-
"eval_samples_per_second": 12620.958,
|
| 2814 |
-
"eval_steps_per_second": 6.185,
|
| 2815 |
-
"step": 18700
|
| 2816 |
-
},
|
| 2817 |
-
{
|
| 2818 |
-
"epoch": 81.03448275862068,
|
| 2819 |
-
"grad_norm": 0.1379682719707489,
|
| 2820 |
-
"learning_rate": 0.00017429787945419606,
|
| 2821 |
-
"loss": 0.8873,
|
| 2822 |
-
"step": 18800
|
| 2823 |
-
},
|
| 2824 |
-
{
|
| 2825 |
-
"epoch": 81.03448275862068,
|
| 2826 |
-
"eval_loss": 5.695350646972656,
|
| 2827 |
-
"eval_runtime": 9.2531,
|
| 2828 |
-
"eval_samples_per_second": 12790.455,
|
| 2829 |
-
"eval_steps_per_second": 6.268,
|
| 2830 |
-
"step": 18800
|
| 2831 |
-
},
|
| 2832 |
-
{
|
| 2833 |
-
"epoch": 81.46551724137932,
|
| 2834 |
-
"grad_norm": 0.1285446733236313,
|
| 2835 |
-
"learning_rate": 0.00016670264651586397,
|
| 2836 |
-
"loss": 0.8755,
|
| 2837 |
-
"step": 18900
|
| 2838 |
-
},
|
| 2839 |
-
{
|
| 2840 |
-
"epoch": 81.46551724137932,
|
| 2841 |
-
"eval_loss": 5.643267631530762,
|
| 2842 |
-
"eval_runtime": 9.3848,
|
| 2843 |
-
"eval_samples_per_second": 12610.893,
|
| 2844 |
-
"eval_steps_per_second": 6.18,
|
| 2845 |
-
"step": 18900
|
| 2846 |
-
},
|
| 2847 |
-
{
|
| 2848 |
-
"epoch": 81.89655172413794,
|
| 2849 |
-
"grad_norm": 0.12641337513923645,
|
| 2850 |
-
"learning_rate": 0.00015926153715963565,
|
| 2851 |
-
"loss": 0.8836,
|
| 2852 |
-
"step": 19000
|
| 2853 |
-
},
|
| 2854 |
-
{
|
| 2855 |
-
"epoch": 81.89655172413794,
|
| 2856 |
-
"eval_loss": 5.626917839050293,
|
| 2857 |
-
"eval_runtime": 9.2261,
|
| 2858 |
-
"eval_samples_per_second": 12827.886,
|
| 2859 |
-
"eval_steps_per_second": 6.287,
|
| 2860 |
-
"step": 19000
|
| 2861 |
-
},
|
| 2862 |
-
{
|
| 2863 |
-
"epoch": 82.32758620689656,
|
| 2864 |
-
"grad_norm": 0.13148842751979828,
|
| 2865 |
-
"learning_rate": 0.00015197592766544755,
|
| 2866 |
-
"loss": 0.8756,
|
| 2867 |
-
"step": 19100
|
| 2868 |
-
},
|
| 2869 |
-
{
|
| 2870 |
-
"epoch": 82.32758620689656,
|
| 2871 |
-
"eval_loss": 5.652148723602295,
|
| 2872 |
-
"eval_runtime": 9.2465,
|
| 2873 |
-
"eval_samples_per_second": 12799.543,
|
| 2874 |
-
"eval_steps_per_second": 6.273,
|
| 2875 |
-
"step": 19100
|
| 2876 |
-
},
|
| 2877 |
-
{
|
| 2878 |
-
"epoch": 82.75862068965517,
|
| 2879 |
-
"grad_norm": 0.12983547151088715,
|
| 2880 |
-
"learning_rate": 0.00014484716555255916,
|
| 2881 |
-
"loss": 0.8795,
|
| 2882 |
-
"step": 19200
|
| 2883 |
-
},
|
| 2884 |
-
{
|
| 2885 |
-
"epoch": 82.75862068965517,
|
| 2886 |
-
"eval_loss": 5.643835544586182,
|
| 2887 |
-
"eval_runtime": 9.2246,
|
| 2888 |
-
"eval_samples_per_second": 12829.918,
|
| 2889 |
-
"eval_steps_per_second": 6.288,
|
| 2890 |
-
"step": 19200
|
| 2891 |
-
},
|
| 2892 |
-
{
|
| 2893 |
-
"epoch": 83.1896551724138,
|
| 2894 |
-
"grad_norm": 0.13281339406967163,
|
| 2895 |
-
"learning_rate": 0.000137876569330322,
|
| 2896 |
-
"loss": 0.8766,
|
| 2897 |
-
"step": 19300
|
| 2898 |
-
},
|
| 2899 |
-
{
|
| 2900 |
-
"epoch": 83.1896551724138,
|
| 2901 |
-
"eval_loss": 5.681993007659912,
|
| 2902 |
-
"eval_runtime": 9.223,
|
| 2903 |
-
"eval_samples_per_second": 12832.225,
|
| 2904 |
-
"eval_steps_per_second": 6.289,
|
| 2905 |
-
"step": 19300
|
| 2906 |
-
},
|
| 2907 |
-
{
|
| 2908 |
-
"epoch": 83.62068965517241,
|
| 2909 |
-
"grad_norm": 0.1261378824710846,
|
| 2910 |
-
"learning_rate": 0.0001310654282543118,
|
| 2911 |
-
"loss": 0.8739,
|
| 2912 |
-
"step": 19400
|
| 2913 |
-
},
|
| 2914 |
-
{
|
| 2915 |
-
"epoch": 83.62068965517241,
|
| 2916 |
-
"eval_loss": 5.645988464355469,
|
| 2917 |
-
"eval_runtime": 9.5681,
|
| 2918 |
-
"eval_samples_per_second": 12369.283,
|
| 2919 |
-
"eval_steps_per_second": 6.062,
|
| 2920 |
-
"step": 19400
|
| 2921 |
-
},
|
| 2922 |
-
{
|
| 2923 |
-
"epoch": 84.05172413793103,
|
| 2924 |
-
"grad_norm": 0.1342853307723999,
|
| 2925 |
-
"learning_rate": 0.00012441500208787225,
|
| 2926 |
-
"loss": 0.88,
|
| 2927 |
-
"step": 19500
|
| 2928 |
-
},
|
| 2929 |
-
{
|
| 2930 |
-
"epoch": 84.05172413793103,
|
| 2931 |
-
"eval_loss": 5.7274885177612305,
|
| 2932 |
-
"eval_runtime": 9.2591,
|
| 2933 |
-
"eval_samples_per_second": 12782.084,
|
| 2934 |
-
"eval_steps_per_second": 6.264,
|
| 2935 |
-
"step": 19500
|
| 2936 |
-
},
|
| 2937 |
-
{
|
| 2938 |
-
"epoch": 84.48275862068965,
|
| 2939 |
-
"grad_norm": 0.13619554042816162,
|
| 2940 |
-
"learning_rate": 0.00011792652086911582,
|
| 2941 |
-
"loss": 0.8707,
|
| 2942 |
-
"step": 19600
|
| 2943 |
-
},
|
| 2944 |
-
{
|
| 2945 |
-
"epoch": 84.48275862068965,
|
| 2946 |
-
"eval_loss": 5.669314384460449,
|
| 2947 |
-
"eval_runtime": 9.231,
|
| 2948 |
-
"eval_samples_per_second": 12821.08,
|
| 2949 |
-
"eval_steps_per_second": 6.283,
|
| 2950 |
-
"step": 19600
|
| 2951 |
-
},
|
| 2952 |
-
{
|
| 2953 |
-
"epoch": 84.91379310344827,
|
| 2954 |
-
"grad_norm": 0.1309289187192917,
|
| 2955 |
-
"learning_rate": 0.00011160118468341863,
|
| 2956 |
-
"loss": 0.8778,
|
| 2957 |
-
"step": 19700
|
| 2958 |
-
},
|
| 2959 |
-
{
|
| 2960 |
-
"epoch": 84.91379310344827,
|
| 2961 |
-
"eval_loss": 5.653628349304199,
|
| 2962 |
-
"eval_runtime": 9.2387,
|
| 2963 |
-
"eval_samples_per_second": 12810.365,
|
| 2964 |
-
"eval_steps_per_second": 6.278,
|
| 2965 |
-
"step": 19700
|
| 2966 |
-
},
|
| 2967 |
-
{
|
| 2968 |
-
"epoch": 85.34482758620689,
|
| 2969 |
-
"grad_norm": 0.12790584564208984,
|
| 2970 |
-
"learning_rate": 0.00010544016344145713,
|
| 2971 |
-
"loss": 0.8699,
|
| 2972 |
-
"step": 19800
|
| 2973 |
-
},
|
| 2974 |
-
{
|
| 2975 |
-
"epoch": 85.34482758620689,
|
| 2976 |
-
"eval_loss": 5.69779634475708,
|
| 2977 |
-
"eval_runtime": 9.4304,
|
| 2978 |
-
"eval_samples_per_second": 12549.969,
|
| 2979 |
-
"eval_steps_per_second": 6.15,
|
| 2980 |
-
"step": 19800
|
| 2981 |
-
},
|
| 2982 |
-
{
|
| 2983 |
-
"epoch": 85.77586206896552,
|
| 2984 |
-
"grad_norm": 0.125418022274971,
|
| 2985 |
-
"learning_rate": 9.944459666282745e-05,
|
| 2986 |
-
"loss": 0.8734,
|
| 2987 |
-
"step": 19900
|
| 2988 |
-
},
|
| 2989 |
-
{
|
| 2990 |
-
"epoch": 85.77586206896552,
|
| 2991 |
-
"eval_loss": 5.671902656555176,
|
| 2992 |
-
"eval_runtime": 9.407,
|
| 2993 |
-
"eval_samples_per_second": 12581.158,
|
| 2994 |
-
"eval_steps_per_second": 6.166,
|
| 2995 |
-
"step": 19900
|
| 2996 |
-
},
|
| 2997 |
-
{
|
| 2998 |
-
"epoch": 86.20689655172414,
|
| 2999 |
-
"grad_norm": 0.1286143958568573,
|
| 3000 |
-
"learning_rate": 9.361559326528213e-05,
|
| 3001 |
-
"loss": 0.8713,
|
| 3002 |
-
"step": 20000
|
| 3003 |
-
},
|
| 3004 |
-
{
|
| 3005 |
-
"epoch": 86.20689655172414,
|
| 3006 |
-
"eval_loss": 5.720515251159668,
|
| 3007 |
-
"eval_runtime": 9.2375,
|
| 3008 |
-
"eval_samples_per_second": 12812.036,
|
| 3009 |
-
"eval_steps_per_second": 6.279,
|
| 3010 |
-
"step": 20000
|
| 3011 |
-
},
|
| 3012 |
-
{
|
| 3013 |
-
"epoch": 86.63793103448276,
|
| 3014 |
-
"grad_norm": 0.1244572177529335,
|
| 3015 |
-
"learning_rate": 8.795423135962966e-05,
|
| 3016 |
-
"loss": 0.8702,
|
| 3017 |
-
"step": 20100
|
| 3018 |
-
},
|
| 3019 |
-
{
|
| 3020 |
-
"epoch": 86.63793103448276,
|
| 3021 |
-
"eval_loss": 5.679359436035156,
|
| 3022 |
-
"eval_runtime": 9.3749,
|
| 3023 |
-
"eval_samples_per_second": 12624.294,
|
| 3024 |
-
"eval_steps_per_second": 6.187,
|
| 3025 |
-
"step": 20100
|
| 3026 |
-
},
|
| 3027 |
-
{
|
| 3028 |
-
"epoch": 87.06896551724138,
|
| 3029 |
-
"grad_norm": 0.13650184869766235,
|
| 3030 |
-
"learning_rate": 8.246155805033218e-05,
|
| 3031 |
-
"loss": 0.8729,
|
| 3032 |
-
"step": 20200
|
| 3033 |
-
},
|
| 3034 |
-
{
|
| 3035 |
-
"epoch": 87.06896551724138,
|
| 3036 |
-
"eval_loss": 5.74306583404541,
|
| 3037 |
-
"eval_runtime": 9.2113,
|
| 3038 |
-
"eval_samples_per_second": 12848.47,
|
| 3039 |
-
"eval_steps_per_second": 6.297,
|
| 3040 |
-
"step": 20200
|
| 3041 |
-
},
|
| 3042 |
-
{
|
| 3043 |
-
"epoch": 87.5,
|
| 3044 |
-
"grad_norm": 0.1307421624660492,
|
| 3045 |
-
"learning_rate": 7.713858924183448e-05,
|
| 3046 |
-
"loss": 0.8664,
|
| 3047 |
-
"step": 20300
|
| 3048 |
-
},
|
| 3049 |
-
{
|
| 3050 |
-
"epoch": 87.5,
|
| 3051 |
-
"eval_loss": 5.708529472351074,
|
| 3052 |
-
"eval_runtime": 9.4057,
|
| 3053 |
-
"eval_samples_per_second": 12582.911,
|
| 3054 |
-
"eval_steps_per_second": 6.166,
|
| 3055 |
-
"step": 20300
|
| 3056 |
-
},
|
| 3057 |
-
{
|
| 3058 |
-
"epoch": 87.93103448275862,
|
| 3059 |
-
"grad_norm": 0.12468791753053665,
|
| 3060 |
-
"learning_rate": 7.198630945066809e-05,
|
| 3061 |
-
"loss": 0.8717,
|
| 3062 |
-
"step": 20400
|
| 3063 |
-
},
|
| 3064 |
-
{
|
| 3065 |
-
"epoch": 87.93103448275862,
|
| 3066 |
-
"eval_loss": 5.68959903717041,
|
| 3067 |
-
"eval_runtime": 10.135,
|
| 3068 |
-
"eval_samples_per_second": 11677.436,
|
| 3069 |
-
"eval_steps_per_second": 5.723,
|
| 3070 |
-
"step": 20400
|
| 3071 |
-
},
|
| 3072 |
-
{
|
| 3073 |
-
"epoch": 88.36206896551724,
|
| 3074 |
-
"grad_norm": 0.12915968894958496,
|
| 3075 |
-
"learning_rate": 6.70056716233587e-05,
|
| 3076 |
-
"loss": 0.8662,
|
| 3077 |
-
"step": 20500
|
| 3078 |
-
},
|
| 3079 |
-
{
|
| 3080 |
-
"epoch": 88.36206896551724,
|
| 3081 |
-
"eval_loss": 5.714221954345703,
|
| 3082 |
-
"eval_runtime": 9.9287,
|
| 3083 |
-
"eval_samples_per_second": 11920.034,
|
| 3084 |
-
"eval_steps_per_second": 5.842,
|
| 3085 |
-
"step": 20500
|
| 3086 |
-
},
|
| 3087 |
-
{
|
| 3088 |
-
"epoch": 88.79310344827586,
|
| 3089 |
-
"grad_norm": 0.12067535519599915,
|
| 3090 |
-
"learning_rate": 6.219759696017113e-05,
|
| 3091 |
-
"loss": 0.8686,
|
| 3092 |
-
"step": 20600
|
| 3093 |
-
},
|
| 3094 |
-
{
|
| 3095 |
-
"epoch": 88.79310344827586,
|
| 3096 |
-
"eval_loss": 5.706583023071289,
|
| 3097 |
-
"eval_runtime": 9.7773,
|
| 3098 |
-
"eval_samples_per_second": 12104.609,
|
| 3099 |
-
"eval_steps_per_second": 5.932,
|
| 3100 |
-
"step": 20600
|
| 3101 |
-
},
|
| 3102 |
-
{
|
| 3103 |
-
"epoch": 89.22413793103448,
|
| 3104 |
-
"grad_norm": 0.12324505299329758,
|
| 3105 |
-
"learning_rate": 5.7562974744729046e-05,
|
| 3106 |
-
"loss": 0.867,
|
| 3107 |
-
"step": 20700
|
| 3108 |
-
},
|
| 3109 |
-
{
|
| 3110 |
-
"epoch": 89.22413793103448,
|
| 3111 |
-
"eval_loss": 5.7304487228393555,
|
| 3112 |
-
"eval_runtime": 9.5287,
|
| 3113 |
-
"eval_samples_per_second": 12420.512,
|
| 3114 |
-
"eval_steps_per_second": 6.087,
|
| 3115 |
-
"step": 20700
|
| 3116 |
-
},
|
| 3117 |
-
{
|
| 3118 |
-
"epoch": 89.65517241379311,
|
| 3119 |
-
"grad_norm": 0.12154043465852737,
|
| 3120 |
-
"learning_rate": 5.3102662179536295e-05,
|
| 3121 |
-
"loss": 0.8663,
|
| 3122 |
-
"step": 20800
|
| 3123 |
-
},
|
| 3124 |
-
{
|
| 3125 |
-
"epoch": 89.65517241379311,
|
| 3126 |
-
"eval_loss": 5.711974143981934,
|
| 3127 |
-
"eval_runtime": 9.2625,
|
| 3128 |
-
"eval_samples_per_second": 12777.417,
|
| 3129 |
-
"eval_steps_per_second": 6.262,
|
| 3130 |
-
"step": 20800
|
| 3131 |
-
},
|
| 3132 |
-
{
|
| 3133 |
-
"epoch": 90.08620689655173,
|
| 3134 |
-
"grad_norm": 0.12663687765598297,
|
| 3135 |
-
"learning_rate": 4.881748422743082e-05,
|
| 3136 |
-
"loss": 0.8673,
|
| 3137 |
-
"step": 20900
|
| 3138 |
-
},
|
| 3139 |
-
{
|
| 3140 |
-
"epoch": 90.08620689655173,
|
| 3141 |
-
"eval_loss": 5.735599994659424,
|
| 3142 |
-
"eval_runtime": 9.79,
|
| 3143 |
-
"eval_samples_per_second": 12088.923,
|
| 3144 |
-
"eval_steps_per_second": 5.924,
|
| 3145 |
-
"step": 20900
|
| 3146 |
-
},
|
| 3147 |
-
{
|
| 3148 |
-
"epoch": 90.51724137931035,
|
| 3149 |
-
"grad_norm": 0.12401026487350464,
|
| 3150 |
-
"learning_rate": 4.474845260451621e-05,
|
| 3151 |
-
"loss": 0.864,
|
| 3152 |
-
"step": 21000
|
| 3153 |
-
},
|
| 3154 |
-
{
|
| 3155 |
-
"epoch": 90.51724137931035,
|
| 3156 |
-
"eval_loss": 5.719780445098877,
|
| 3157 |
-
"eval_runtime": 9.8841,
|
| 3158 |
-
"eval_samples_per_second": 11973.938,
|
| 3159 |
-
"eval_steps_per_second": 5.868,
|
| 3160 |
-
"step": 21000
|
| 3161 |
-
},
|
| 3162 |
-
{
|
| 3163 |
-
"epoch": 90.94827586206897,
|
| 3164 |
-
"grad_norm": 0.13143125176429749,
|
| 3165 |
-
"learning_rate": 4.081411852439809e-05,
|
| 3166 |
-
"loss": 0.8669,
|
| 3167 |
-
"step": 21100
|
| 3168 |
-
},
|
| 3169 |
-
{
|
| 3170 |
-
"epoch": 90.94827586206897,
|
| 3171 |
-
"eval_loss": 5.718562602996826,
|
| 3172 |
-
"eval_runtime": 9.4018,
|
| 3173 |
-
"eval_samples_per_second": 12588.15,
|
| 3174 |
-
"eval_steps_per_second": 6.169,
|
| 3175 |
-
"step": 21100
|
| 3176 |
-
},
|
| 3177 |
-
{
|
| 3178 |
-
"epoch": 91.37931034482759,
|
| 3179 |
-
"grad_norm": 0.11996802687644958,
|
| 3180 |
-
"learning_rate": 3.705719190073964e-05,
|
| 3181 |
-
"loss": 0.8635,
|
| 3182 |
-
"step": 21200
|
| 3183 |
-
},
|
| 3184 |
-
{
|
| 3185 |
-
"epoch": 91.37931034482759,
|
| 3186 |
-
"eval_loss": 5.731278896331787,
|
| 3187 |
-
"eval_runtime": 9.8189,
|
| 3188 |
-
"eval_samples_per_second": 12053.388,
|
| 3189 |
-
"eval_steps_per_second": 5.907,
|
| 3190 |
-
"step": 21200
|
| 3191 |
-
},
|
| 3192 |
-
{
|
| 3193 |
-
"epoch": 91.8103448275862,
|
| 3194 |
-
"grad_norm": 0.13093972206115723,
|
| 3195 |
-
"learning_rate": 3.3478367600728754e-05,
|
| 3196 |
-
"loss": 0.8638,
|
| 3197 |
-
"step": 21300
|
| 3198 |
-
},
|
| 3199 |
-
{
|
| 3200 |
-
"epoch": 91.8103448275862,
|
| 3201 |
-
"eval_loss": 5.722977161407471,
|
| 3202 |
-
"eval_runtime": 9.5816,
|
| 3203 |
-
"eval_samples_per_second": 12351.934,
|
| 3204 |
-
"eval_steps_per_second": 6.053,
|
| 3205 |
-
"step": 21300
|
| 3206 |
-
},
|
| 3207 |
-
{
|
| 3208 |
-
"epoch": 92.24137931034483,
|
| 3209 |
-
"grad_norm": 0.12292136996984482,
|
| 3210 |
-
"learning_rate": 3.0078307550409967e-05,
|
| 3211 |
-
"loss": 0.8643,
|
| 3212 |
-
"step": 21400
|
| 3213 |
-
},
|
| 3214 |
-
{
|
| 3215 |
-
"epoch": 92.24137931034483,
|
| 3216 |
-
"eval_loss": 5.742223262786865,
|
| 3217 |
-
"eval_runtime": 10.257,
|
| 3218 |
-
"eval_samples_per_second": 11538.52,
|
| 3219 |
-
"eval_steps_per_second": 5.655,
|
| 3220 |
-
"step": 21400
|
| 3221 |
-
},
|
| 3222 |
-
{
|
| 3223 |
-
"epoch": 92.67241379310344,
|
| 3224 |
-
"grad_norm": 0.12908169627189636,
|
| 3225 |
-
"learning_rate": 2.685764061225615e-05,
|
| 3226 |
-
"loss": 0.8628,
|
| 3227 |
-
"step": 21500
|
| 3228 |
-
},
|
| 3229 |
-
{
|
| 3230 |
-
"epoch": 92.67241379310344,
|
| 3231 |
-
"eval_loss": 5.730621814727783,
|
| 3232 |
-
"eval_runtime": 9.8371,
|
| 3233 |
-
"eval_samples_per_second": 12031.124,
|
| 3234 |
-
"eval_steps_per_second": 5.896,
|
| 3235 |
-
"step": 21500
|
| 3236 |
-
},
|
| 3237 |
-
{
|
| 3238 |
-
"epoch": 93.10344827586206,
|
| 3239 |
-
"grad_norm": 0.12206296622753143,
|
| 3240 |
-
"learning_rate": 2.381696246885634e-05,
|
| 3241 |
-
"loss": 0.8639,
|
| 3242 |
-
"step": 21600
|
| 3243 |
-
},
|
| 3244 |
-
{
|
| 3245 |
-
"epoch": 93.10344827586206,
|
| 3246 |
-
"eval_loss": 5.747194290161133,
|
| 3247 |
-
"eval_runtime": 10.0468,
|
| 3248 |
-
"eval_samples_per_second": 11779.952,
|
| 3249 |
-
"eval_steps_per_second": 5.773,
|
| 3250 |
-
"step": 21600
|
| 3251 |
-
},
|
| 3252 |
-
{
|
| 3253 |
-
"epoch": 93.53448275862068,
|
| 3254 |
-
"grad_norm": 0.12943461537361145,
|
| 3255 |
-
"learning_rate": 2.0956835512741523e-05,
|
| 3256 |
-
"loss": 0.8617,
|
| 3257 |
-
"step": 21700
|
| 3258 |
-
},
|
| 3259 |
-
{
|
| 3260 |
-
"epoch": 93.53448275862068,
|
| 3261 |
-
"eval_loss": 5.736154556274414,
|
| 3262 |
-
"eval_runtime": 9.5983,
|
| 3263 |
-
"eval_samples_per_second": 12330.438,
|
| 3264 |
-
"eval_steps_per_second": 6.043,
|
| 3265 |
-
"step": 21700
|
| 3266 |
-
},
|
| 3267 |
-
{
|
| 3268 |
-
"epoch": 93.96551724137932,
|
| 3269 |
-
"grad_norm": 0.11701935529708862,
|
| 3270 |
-
"learning_rate": 1.8277788742365964e-05,
|
| 3271 |
-
"loss": 0.8638,
|
| 3272 |
-
"step": 21800
|
| 3273 |
-
},
|
| 3274 |
-
{
|
| 3275 |
-
"epoch": 93.96551724137932,
|
| 3276 |
-
"eval_loss": 5.730475425720215,
|
| 3277 |
-
"eval_runtime": 9.2662,
|
| 3278 |
-
"eval_samples_per_second": 12772.39,
|
| 3279 |
-
"eval_steps_per_second": 6.259,
|
| 3280 |
-
"step": 21800
|
| 3281 |
-
},
|
| 3282 |
-
{
|
| 3283 |
-
"epoch": 94.39655172413794,
|
| 3284 |
-
"grad_norm": 0.12347536534070969,
|
| 3285 |
-
"learning_rate": 1.5780317664264798e-05,
|
| 3286 |
-
"loss": 0.8614,
|
| 3287 |
-
"step": 21900
|
| 3288 |
-
},
|
| 3289 |
-
{
|
| 3290 |
-
"epoch": 94.39655172413794,
|
| 3291 |
-
"eval_loss": 5.749207019805908,
|
| 3292 |
-
"eval_runtime": 10.0776,
|
| 3293 |
-
"eval_samples_per_second": 11743.987,
|
| 3294 |
-
"eval_steps_per_second": 5.755,
|
| 3295 |
-
"step": 21900
|
| 3296 |
-
},
|
| 3297 |
-
{
|
| 3298 |
-
"epoch": 94.82758620689656,
|
| 3299 |
-
"grad_norm": 0.1210562139749527,
|
| 3300 |
-
"learning_rate": 1.3464884201409122e-05,
|
| 3301 |
-
"loss": 0.8618,
|
| 3302 |
-
"step": 22000
|
| 3303 |
-
},
|
| 3304 |
-
{
|
| 3305 |
-
"epoch": 94.82758620689656,
|
| 3306 |
-
"eval_loss": 5.740473747253418,
|
| 3307 |
-
"eval_runtime": 9.8545,
|
| 3308 |
-
"eval_samples_per_second": 12009.888,
|
| 3309 |
-
"eval_steps_per_second": 5.886,
|
| 3310 |
-
"step": 22000
|
| 3311 |
-
},
|
| 3312 |
-
{
|
| 3313 |
-
"epoch": 95.25862068965517,
|
| 3314 |
-
"grad_norm": 0.1231653168797493,
|
| 3315 |
-
"learning_rate": 1.1331916607768001e-05,
|
| 3316 |
-
"loss": 0.8614,
|
| 3317 |
-
"step": 22100
|
| 3318 |
-
},
|
| 3319 |
-
{
|
| 3320 |
-
"epoch": 95.25862068965517,
|
| 3321 |
-
"eval_loss": 5.748401641845703,
|
| 3322 |
-
"eval_runtime": 9.3274,
|
| 3323 |
-
"eval_samples_per_second": 12688.59,
|
| 3324 |
-
"eval_steps_per_second": 6.218,
|
| 3325 |
-
"step": 22100
|
| 3326 |
-
},
|
| 3327 |
-
{
|
| 3328 |
-
"epoch": 95.6896551724138,
|
| 3329 |
-
"grad_norm": 0.12054872512817383,
|
| 3330 |
-
"learning_rate": 9.381809389101825e-06,
|
| 3331 |
-
"loss": 0.8606,
|
| 3332 |
-
"step": 22200
|
| 3333 |
-
},
|
| 3334 |
-
{
|
| 3335 |
-
"epoch": 95.6896551724138,
|
| 3336 |
-
"eval_loss": 5.742131233215332,
|
| 3337 |
-
"eval_runtime": 9.7151,
|
| 3338 |
-
"eval_samples_per_second": 12182.214,
|
| 3339 |
-
"eval_steps_per_second": 5.97,
|
| 3340 |
-
"step": 22200
|
| 3341 |
-
},
|
| 3342 |
-
{
|
| 3343 |
-
"epoch": 96.12068965517241,
|
| 3344 |
-
"grad_norm": 0.12231267988681793,
|
| 3345 |
-
"learning_rate": 7.614923229995796e-06,
|
| 3346 |
-
"loss": 0.8617,
|
| 3347 |
-
"step": 22300
|
| 3348 |
-
},
|
| 3349 |
-
{
|
| 3350 |
-
"epoch": 96.12068965517241,
|
| 3351 |
-
"eval_loss": 5.743917942047119,
|
| 3352 |
-
"eval_runtime": 9.8384,
|
| 3353 |
-
"eval_samples_per_second": 12029.513,
|
| 3354 |
-
"eval_steps_per_second": 5.895,
|
| 3355 |
-
"step": 22300
|
| 3356 |
-
},
|
| 3357 |
-
{
|
| 3358 |
-
"epoch": 96.55172413793103,
|
| 3359 |
-
"grad_norm": 0.12903857231140137,
|
| 3360 |
-
"learning_rate": 6.03158492714806e-06,
|
| 3361 |
-
"loss": 0.8606,
|
| 3362 |
-
"step": 22400
|
| 3363 |
-
},
|
| 3364 |
-
{
|
| 3365 |
-
"epoch": 96.55172413793103,
|
| 3366 |
-
"eval_loss": 5.747518062591553,
|
| 3367 |
-
"eval_runtime": 10.0786,
|
| 3368 |
-
"eval_samples_per_second": 11742.801,
|
| 3369 |
-
"eval_steps_per_second": 5.755,
|
| 3370 |
-
"step": 22400
|
| 3371 |
-
},
|
| 3372 |
-
{
|
| 3373 |
-
"epoch": 96.98275862068965,
|
| 3374 |
-
"grad_norm": 0.12624970078468323,
|
| 3375 |
-
"learning_rate": 4.632087328927947e-06,
|
| 3376 |
-
"loss": 0.8612,
|
| 3377 |
-
"step": 22500
|
| 3378 |
-
},
|
| 3379 |
-
{
|
| 3380 |
-
"epoch": 96.98275862068965,
|
| 3381 |
-
"eval_loss": 5.744797229766846,
|
| 3382 |
-
"eval_runtime": 9.9675,
|
| 3383 |
-
"eval_samples_per_second": 11873.695,
|
| 3384 |
-
"eval_steps_per_second": 5.819,
|
| 3385 |
-
"step": 22500
|
| 3386 |
-
},
|
| 3387 |
-
{
|
| 3388 |
-
"epoch": 97.41379310344827,
|
| 3389 |
-
"grad_norm": 0.11606816947460175,
|
| 3390 |
-
"learning_rate": 3.4166892812107496e-06,
|
| 3391 |
-
"loss": 0.8601,
|
| 3392 |
-
"step": 22600
|
| 3393 |
-
},
|
| 3394 |
-
{
|
| 3395 |
-
"epoch": 97.41379310344827,
|
| 3396 |
-
"eval_loss": 5.747043609619141,
|
| 3397 |
-
"eval_runtime": 9.7354,
|
| 3398 |
-
"eval_samples_per_second": 12156.826,
|
| 3399 |
-
"eval_steps_per_second": 5.958,
|
| 3400 |
-
"step": 22600
|
| 3401 |
-
},
|
| 3402 |
-
{
|
| 3403 |
-
"epoch": 97.84482758620689,
|
| 3404 |
-
"grad_norm": 0.12005724757909775,
|
| 3405 |
-
"learning_rate": 2.3856155795032307e-06,
|
| 3406 |
-
"loss": 0.8606,
|
| 3407 |
-
"step": 22700
|
| 3408 |
-
},
|
| 3409 |
-
{
|
| 3410 |
-
"epoch": 97.84482758620689,
|
| 3411 |
-
"eval_loss": 5.7480788230896,
|
| 3412 |
-
"eval_runtime": 9.7932,
|
| 3413 |
-
"eval_samples_per_second": 12085.032,
|
| 3414 |
-
"eval_steps_per_second": 5.922,
|
| 3415 |
-
"step": 22700
|
| 3416 |
-
},
|
| 3417 |
-
{
|
| 3418 |
-
"epoch": 98.27586206896552,
|
| 3419 |
-
"grad_norm": 0.12075820565223694,
|
| 3420 |
-
"learning_rate": 1.5390569273660005e-06,
|
| 3421 |
-
"loss": 0.8598,
|
| 3422 |
-
"step": 22800
|
| 3423 |
-
},
|
| 3424 |
-
{
|
| 3425 |
-
"epoch": 98.27586206896552,
|
| 3426 |
-
"eval_loss": 5.749686241149902,
|
| 3427 |
-
"eval_runtime": 9.95,
|
| 3428 |
-
"eval_samples_per_second": 11894.516,
|
| 3429 |
-
"eval_steps_per_second": 5.829,
|
| 3430 |
-
"step": 22800
|
| 3431 |
-
},
|
| 3432 |
-
{
|
| 3433 |
-
"epoch": 98.70689655172414,
|
| 3434 |
-
"grad_norm": 0.12352725863456726,
|
| 3435 |
-
"learning_rate": 8.771699011416167e-07,
|
| 3436 |
-
"loss": 0.8598,
|
| 3437 |
-
"step": 22900
|
| 3438 |
-
},
|
| 3439 |
-
{
|
| 3440 |
-
"epoch": 98.70689655172414,
|
| 3441 |
-
"eval_loss": 5.7505316734313965,
|
| 3442 |
-
"eval_runtime": 9.3854,
|
| 3443 |
-
"eval_samples_per_second": 12610.145,
|
| 3444 |
-
"eval_steps_per_second": 6.18,
|
| 3445 |
-
"step": 22900
|
| 3446 |
-
},
|
| 3447 |
-
{
|
| 3448 |
-
"epoch": 99.13793103448276,
|
| 3449 |
-
"grad_norm": 0.11930395662784576,
|
| 3450 |
-
"learning_rate": 4.0007692099508495e-07,
|
| 3451 |
-
"loss": 0.8599,
|
| 3452 |
-
"step": 23000
|
| 3453 |
-
},
|
| 3454 |
-
{
|
| 3455 |
-
"epoch": 99.13793103448276,
|
| 3456 |
-
"eval_loss": 5.750540733337402,
|
| 3457 |
-
"eval_runtime": 9.2142,
|
| 3458 |
-
"eval_samples_per_second": 12844.449,
|
| 3459 |
-
"eval_steps_per_second": 6.295,
|
| 3460 |
-
"step": 23000
|
| 3461 |
-
},
|
| 3462 |
-
{
|
| 3463 |
-
"epoch": 99.56896551724138,
|
| 3464 |
-
"grad_norm": 0.11672677099704742,
|
| 3465 |
-
"learning_rate": 1.0786622827108072e-07,
|
| 3466 |
-
"loss": 0.8603,
|
| 3467 |
-
"step": 23100
|
| 3468 |
-
},
|
| 3469 |
-
{
|
| 3470 |
-
"epoch": 99.56896551724138,
|
| 3471 |
-
"eval_loss": 5.750354766845703,
|
| 3472 |
-
"eval_runtime": 9.2285,
|
| 3473 |
-
"eval_samples_per_second": 12824.547,
|
| 3474 |
-
"eval_steps_per_second": 6.285,
|
| 3475 |
-
"step": 23100
|
| 3476 |
-
}
|
| 3477 |
-
],
|
| 3478 |
-
"logging_steps": 100,
|
| 3479 |
-
"max_steps": 23200,
|
| 3480 |
-
"num_input_tokens_seen": 0,
|
| 3481 |
-
"num_train_epochs": 100,
|
| 3482 |
-
"save_steps": 100,
|
| 3483 |
-
"stateful_callbacks": {
|
| 3484 |
-
"TrainerControl": {
|
| 3485 |
-
"args": {
|
| 3486 |
-
"should_epoch_stop": false,
|
| 3487 |
-
"should_evaluate": false,
|
| 3488 |
-
"should_log": false,
|
| 3489 |
-
"should_save": true,
|
| 3490 |
-
"should_training_stop": false
|
| 3491 |
-
},
|
| 3492 |
-
"attributes": {}
|
| 3493 |
-
}
|
| 3494 |
-
},
|
| 3495 |
-
"total_flos": 1.5693199771340636e+18,
|
| 3496 |
-
"train_batch_size": 256,
|
| 3497 |
-
"trial_name": null,
|
| 3498 |
-
"trial_params": null
|
| 3499 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:9617fbe5a0c3abe149306a96ad0a9d4a3ca9a552041eae0dde931fc7e7d5e0bf
|
| 3 |
-
size 5432
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/model_SAD/checkpoint/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
gpt2cocoSAD/tokenized_data_SAD/dataset_dict.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"splits": ["train", "test"]}
|
|
|
|
|
|
gpt2cocoSAD/tokenized_data_SAD/test/data-00000-of-00001.arrow
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:f03321f4766876b1f90d58a01bc178d49183785fb5a314342037dad68d68343f
|
| 3 |
-
size 120516976
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/tokenized_data_SAD/test/dataset_info.json
DELETED
|
@@ -1,49 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"citation": "",
|
| 3 |
-
"description": "",
|
| 4 |
-
"features": {
|
| 5 |
-
"similarity": {
|
| 6 |
-
"dtype": "float32",
|
| 7 |
-
"_type": "Value"
|
| 8 |
-
},
|
| 9 |
-
"aesthetics_score": {
|
| 10 |
-
"dtype": "float32",
|
| 11 |
-
"_type": "Value"
|
| 12 |
-
},
|
| 13 |
-
"IQAs": {
|
| 14 |
-
"dtype": "float32",
|
| 15 |
-
"_type": "Value"
|
| 16 |
-
},
|
| 17 |
-
"prompt": {
|
| 18 |
-
"dtype": "string",
|
| 19 |
-
"_type": "Value"
|
| 20 |
-
},
|
| 21 |
-
"query": {
|
| 22 |
-
"dtype": "string",
|
| 23 |
-
"_type": "Value"
|
| 24 |
-
},
|
| 25 |
-
"input_ids": {
|
| 26 |
-
"feature": {
|
| 27 |
-
"dtype": "int32",
|
| 28 |
-
"_type": "Value"
|
| 29 |
-
},
|
| 30 |
-
"_type": "List"
|
| 31 |
-
},
|
| 32 |
-
"attention_mask": {
|
| 33 |
-
"feature": {
|
| 34 |
-
"dtype": "int8",
|
| 35 |
-
"_type": "Value"
|
| 36 |
-
},
|
| 37 |
-
"_type": "List"
|
| 38 |
-
},
|
| 39 |
-
"labels": {
|
| 40 |
-
"feature": {
|
| 41 |
-
"dtype": "int64",
|
| 42 |
-
"_type": "Value"
|
| 43 |
-
},
|
| 44 |
-
"_type": "List"
|
| 45 |
-
}
|
| 46 |
-
},
|
| 47 |
-
"homepage": "",
|
| 48 |
-
"license": ""
|
| 49 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/tokenized_data_SAD/test/state.json
DELETED
|
@@ -1,22 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_data_files": [
|
| 3 |
-
{
|
| 4 |
-
"filename": "data-00000-of-00001.arrow"
|
| 5 |
-
}
|
| 6 |
-
],
|
| 7 |
-
"_fingerprint": "6f9a3d303ecf4724",
|
| 8 |
-
"_format_columns": [
|
| 9 |
-
"IQAs",
|
| 10 |
-
"aesthetics_score",
|
| 11 |
-
"attention_mask",
|
| 12 |
-
"input_ids",
|
| 13 |
-
"labels",
|
| 14 |
-
"prompt",
|
| 15 |
-
"query",
|
| 16 |
-
"similarity"
|
| 17 |
-
],
|
| 18 |
-
"_format_kwargs": {},
|
| 19 |
-
"_format_type": "torch",
|
| 20 |
-
"_output_all_columns": false,
|
| 21 |
-
"_split": null
|
| 22 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/tokenized_data_SAD/train/data-00000-of-00001.arrow
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:69b57887cf3f44daf4894e056d56ae569e8052d1f3095fd0eb15c1b3faf264ed
|
| 3 |
-
size 482053608
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/tokenized_data_SAD/train/dataset_info.json
DELETED
|
@@ -1,49 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"citation": "",
|
| 3 |
-
"description": "",
|
| 4 |
-
"features": {
|
| 5 |
-
"similarity": {
|
| 6 |
-
"dtype": "float32",
|
| 7 |
-
"_type": "Value"
|
| 8 |
-
},
|
| 9 |
-
"aesthetics_score": {
|
| 10 |
-
"dtype": "float32",
|
| 11 |
-
"_type": "Value"
|
| 12 |
-
},
|
| 13 |
-
"IQAs": {
|
| 14 |
-
"dtype": "float32",
|
| 15 |
-
"_type": "Value"
|
| 16 |
-
},
|
| 17 |
-
"prompt": {
|
| 18 |
-
"dtype": "string",
|
| 19 |
-
"_type": "Value"
|
| 20 |
-
},
|
| 21 |
-
"query": {
|
| 22 |
-
"dtype": "string",
|
| 23 |
-
"_type": "Value"
|
| 24 |
-
},
|
| 25 |
-
"input_ids": {
|
| 26 |
-
"feature": {
|
| 27 |
-
"dtype": "int32",
|
| 28 |
-
"_type": "Value"
|
| 29 |
-
},
|
| 30 |
-
"_type": "List"
|
| 31 |
-
},
|
| 32 |
-
"attention_mask": {
|
| 33 |
-
"feature": {
|
| 34 |
-
"dtype": "int8",
|
| 35 |
-
"_type": "Value"
|
| 36 |
-
},
|
| 37 |
-
"_type": "List"
|
| 38 |
-
},
|
| 39 |
-
"labels": {
|
| 40 |
-
"feature": {
|
| 41 |
-
"dtype": "int64",
|
| 42 |
-
"_type": "Value"
|
| 43 |
-
},
|
| 44 |
-
"_type": "List"
|
| 45 |
-
}
|
| 46 |
-
},
|
| 47 |
-
"homepage": "",
|
| 48 |
-
"license": ""
|
| 49 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gpt2cocoSAD/tokenized_data_SAD/train/state.json
DELETED
|
@@ -1,22 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_data_files": [
|
| 3 |
-
{
|
| 4 |
-
"filename": "data-00000-of-00001.arrow"
|
| 5 |
-
}
|
| 6 |
-
],
|
| 7 |
-
"_fingerprint": "faf36a2481d8a52b",
|
| 8 |
-
"_format_columns": [
|
| 9 |
-
"IQAs",
|
| 10 |
-
"aesthetics_score",
|
| 11 |
-
"attention_mask",
|
| 12 |
-
"input_ids",
|
| 13 |
-
"labels",
|
| 14 |
-
"prompt",
|
| 15 |
-
"query",
|
| 16 |
-
"similarity"
|
| 17 |
-
],
|
| 18 |
-
"_format_kwargs": {},
|
| 19 |
-
"_format_type": "torch",
|
| 20 |
-
"_output_all_columns": false,
|
| 21 |
-
"_split": null
|
| 22 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|