Training in progress, step 500, checkpoint
Browse files- last-checkpoint/config.json +4 -4
- last-checkpoint/generation_config.json +3 -3
- last-checkpoint/model.safetensors +2 -2
- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +1 -4
- last-checkpoint/trainer_state.json +362 -11
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/config.json
CHANGED
|
@@ -5,10 +5,10 @@
|
|
| 5 |
"GPT2LMHeadModel"
|
| 6 |
],
|
| 7 |
"attn_pdrop": 0.0,
|
| 8 |
-
"bos_token_id":
|
| 9 |
"dtype": "float32",
|
| 10 |
"embd_pdrop": 0.0,
|
| 11 |
-
"eos_token_id":
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"layer_norm_epsilon": 1e-05,
|
| 14 |
"model_type": "gpt2",
|
|
@@ -18,7 +18,7 @@
|
|
| 18 |
"n_inner": 3072,
|
| 19 |
"n_layer": 8,
|
| 20 |
"n_positions": 1024,
|
| 21 |
-
"pad_token_id":
|
| 22 |
"reorder_and_upcast_attn": false,
|
| 23 |
"resid_pdrop": 0.0,
|
| 24 |
"scale_attn_by_inverse_layer_idx": false,
|
|
@@ -31,5 +31,5 @@
|
|
| 31 |
"tie_word_embeddings": true,
|
| 32 |
"transformers_version": "5.0.0",
|
| 33 |
"use_cache": false,
|
| 34 |
-
"vocab_size":
|
| 35 |
}
|
|
|
|
| 5 |
"GPT2LMHeadModel"
|
| 6 |
],
|
| 7 |
"attn_pdrop": 0.0,
|
| 8 |
+
"bos_token_id": 2,
|
| 9 |
"dtype": "float32",
|
| 10 |
"embd_pdrop": 0.0,
|
| 11 |
+
"eos_token_id": 3,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"layer_norm_epsilon": 1e-05,
|
| 14 |
"model_type": "gpt2",
|
|
|
|
| 18 |
"n_inner": 3072,
|
| 19 |
"n_layer": 8,
|
| 20 |
"n_positions": 1024,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
"reorder_and_upcast_attn": false,
|
| 23 |
"resid_pdrop": 0.0,
|
| 24 |
"scale_attn_by_inverse_layer_idx": false,
|
|
|
|
| 31 |
"tie_word_embeddings": true,
|
| 32 |
"transformers_version": "5.0.0",
|
| 33 |
"use_cache": false,
|
| 34 |
+
"vocab_size": 32000
|
| 35 |
}
|
last-checkpoint/generation_config.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
-
"bos_token_id":
|
| 4 |
"eos_token_id": [
|
| 5 |
-
|
| 6 |
],
|
| 7 |
"output_attentions": false,
|
| 8 |
"output_hidden_states": false,
|
| 9 |
-
"pad_token_id":
|
| 10 |
"transformers_version": "5.0.0",
|
| 11 |
"use_cache": true
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
"eos_token_id": [
|
| 5 |
+
3
|
| 6 |
],
|
| 7 |
"output_attentions": false,
|
| 8 |
"output_hidden_states": false,
|
| 9 |
+
"pad_token_id": 0,
|
| 10 |
"transformers_version": "5.0.0",
|
| 11 |
"use_cache": true
|
| 12 |
}
|
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87ff9a10f70d200b2c856dee103d85c0b4769807377164ae058876c9b2f8cdf4
|
| 3 |
+
size 328277848
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3e3d47782f2acc46ebaf4d2a3bfa3f0989afdba6a7eed3d7d950f2b764c9119
|
| 3 |
+
size 318646859
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a9464afe392ee166598218bbc5440e93bb5f6227028ba0c26fc8e4fdcf73ae8
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d6f69db244377919464a655cd8dc38a3ecd36738e8ab7fd789261995d39f57a
|
| 3 |
size 1465
|
last-checkpoint/tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/tokenizer_config.json
CHANGED
|
@@ -1,13 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space": null,
|
| 3 |
"backend": "tokenizers",
|
| 4 |
"bos_token": "<s>",
|
| 5 |
-
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "</s>",
|
| 7 |
"is_local": true,
|
| 8 |
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
"pad_token": "<pad>",
|
| 10 |
"tokenizer_class": "TokenizersBackend",
|
| 11 |
-
"unk_token": "<unk>"
|
| 12 |
-
"use_default_system_prompt": false
|
| 13 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"backend": "tokenizers",
|
| 3 |
"bos_token": "<s>",
|
|
|
|
| 4 |
"eos_token": "</s>",
|
| 5 |
"is_local": true,
|
| 6 |
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
"pad_token": "<pad>",
|
| 8 |
"tokenizer_class": "TokenizersBackend",
|
| 9 |
+
"unk_token": "<unk>"
|
|
|
|
| 10 |
}
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,30 +2,381 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 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.
|
| 14 |
-
"grad_norm":
|
| 15 |
"learning_rate": 0.0,
|
| 16 |
-
"loss":
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch":
|
| 21 |
-
"grad_norm":
|
| 22 |
"learning_rate": 1.3499999999999998e-06,
|
| 23 |
-
"loss":
|
| 24 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
}
|
| 26 |
],
|
| 27 |
"logging_steps": 10,
|
| 28 |
-
"max_steps":
|
| 29 |
"num_input_tokens_seen": 0,
|
| 30 |
"num_train_epochs": 2,
|
| 31 |
"save_steps": 500,
|
|
@@ -36,12 +387,12 @@
|
|
| 36 |
"should_evaluate": false,
|
| 37 |
"should_log": false,
|
| 38 |
"should_save": true,
|
| 39 |
-
"should_training_stop":
|
| 40 |
},
|
| 41 |
"attributes": {}
|
| 42 |
}
|
| 43 |
},
|
| 44 |
-
"total_flos":
|
| 45 |
"train_batch_size": 48,
|
| 46 |
"trial_name": null,
|
| 47 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.08447372867038351,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"epoch": 0.00016894745734076703,
|
| 14 |
+
"grad_norm": 6.621576309204102,
|
| 15 |
"learning_rate": 0.0,
|
| 16 |
+
"loss": 10.540443420410156,
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
| 20 |
+
"epoch": 0.0016894745734076701,
|
| 21 |
+
"grad_norm": 6.755827903747559,
|
| 22 |
"learning_rate": 1.3499999999999998e-06,
|
| 23 |
+
"loss": 10.498292711046007,
|
| 24 |
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0033789491468153403,
|
| 28 |
+
"grad_norm": 5.475645542144775,
|
| 29 |
+
"learning_rate": 2.85e-06,
|
| 30 |
+
"loss": 10.21649169921875,
|
| 31 |
+
"step": 20
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.00506842372022301,
|
| 35 |
+
"grad_norm": 2.392394781112671,
|
| 36 |
+
"learning_rate": 4.35e-06,
|
| 37 |
+
"loss": 9.751205444335938,
|
| 38 |
+
"step": 30
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0067578982936306806,
|
| 42 |
+
"grad_norm": 2.019033670425415,
|
| 43 |
+
"learning_rate": 5.85e-06,
|
| 44 |
+
"loss": 9.445993041992187,
|
| 45 |
+
"step": 40
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.00844737286703835,
|
| 49 |
+
"grad_norm": 1.1508617401123047,
|
| 50 |
+
"learning_rate": 7.35e-06,
|
| 51 |
+
"loss": 9.269256591796875,
|
| 52 |
+
"step": 50
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.01013684744044602,
|
| 56 |
+
"grad_norm": 0.9643108248710632,
|
| 57 |
+
"learning_rate": 8.849999999999998e-06,
|
| 58 |
+
"loss": 9.148248291015625,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.011826322013853691,
|
| 63 |
+
"grad_norm": 0.9441804885864258,
|
| 64 |
+
"learning_rate": 1.035e-05,
|
| 65 |
+
"loss": 9.042961120605469,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.013515796587261361,
|
| 70 |
+
"grad_norm": 0.8737426996231079,
|
| 71 |
+
"learning_rate": 1.1849999999999998e-05,
|
| 72 |
+
"loss": 8.958677673339844,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.015205271160669031,
|
| 77 |
+
"grad_norm": 0.7889962792396545,
|
| 78 |
+
"learning_rate": 1.3349999999999998e-05,
|
| 79 |
+
"loss": 8.854808044433593,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.0168947457340767,
|
| 84 |
+
"grad_norm": 0.8155699968338013,
|
| 85 |
+
"learning_rate": 1.485e-05,
|
| 86 |
+
"loss": 8.736964416503906,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.018584220307484373,
|
| 91 |
+
"grad_norm": 0.686811625957489,
|
| 92 |
+
"learning_rate": 1.6349999999999998e-05,
|
| 93 |
+
"loss": 8.659473419189453,
|
| 94 |
+
"step": 110
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.02027369488089204,
|
| 98 |
+
"grad_norm": 0.6954357624053955,
|
| 99 |
+
"learning_rate": 1.7849999999999997e-05,
|
| 100 |
+
"loss": 8.550489807128907,
|
| 101 |
+
"step": 120
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.021963169454299714,
|
| 105 |
+
"grad_norm": 0.6710366010665894,
|
| 106 |
+
"learning_rate": 1.935e-05,
|
| 107 |
+
"loss": 8.454399108886719,
|
| 108 |
+
"step": 130
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.023652644027707382,
|
| 112 |
+
"grad_norm": 0.5743041634559631,
|
| 113 |
+
"learning_rate": 2.085e-05,
|
| 114 |
+
"loss": 8.361704254150391,
|
| 115 |
+
"step": 140
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.025342118601115054,
|
| 119 |
+
"grad_norm": 0.5449837446212769,
|
| 120 |
+
"learning_rate": 2.2349999999999998e-05,
|
| 121 |
+
"loss": 8.286068725585938,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.027031593174522722,
|
| 126 |
+
"grad_norm": 0.6015759706497192,
|
| 127 |
+
"learning_rate": 2.3849999999999997e-05,
|
| 128 |
+
"loss": 8.23370819091797,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.028721067747930394,
|
| 133 |
+
"grad_norm": 0.5669003129005432,
|
| 134 |
+
"learning_rate": 2.535e-05,
|
| 135 |
+
"loss": 8.169088745117188,
|
| 136 |
+
"step": 170
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.030410542321338063,
|
| 140 |
+
"grad_norm": 0.42918503284454346,
|
| 141 |
+
"learning_rate": 2.6849999999999995e-05,
|
| 142 |
+
"loss": 8.121391296386719,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.03210001689474573,
|
| 147 |
+
"grad_norm": 0.5449455976486206,
|
| 148 |
+
"learning_rate": 2.8349999999999998e-05,
|
| 149 |
+
"loss": 8.079780578613281,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.0337894914681534,
|
| 154 |
+
"grad_norm": 0.47680142521858215,
|
| 155 |
+
"learning_rate": 2.985e-05,
|
| 156 |
+
"loss": 8.047093200683594,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.035478966041561075,
|
| 161 |
+
"grad_norm": 0.46382999420166016,
|
| 162 |
+
"learning_rate": 3.1349999999999996e-05,
|
| 163 |
+
"loss": 7.9976959228515625,
|
| 164 |
+
"step": 210
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.03716844061496875,
|
| 168 |
+
"grad_norm": 0.4039631485939026,
|
| 169 |
+
"learning_rate": 3.285e-05,
|
| 170 |
+
"loss": 7.981047821044922,
|
| 171 |
+
"step": 220
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.03885791518837641,
|
| 175 |
+
"grad_norm": 0.3981921374797821,
|
| 176 |
+
"learning_rate": 3.435e-05,
|
| 177 |
+
"loss": 7.976937103271484,
|
| 178 |
+
"step": 230
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.04054738976178408,
|
| 182 |
+
"grad_norm": 0.6785397529602051,
|
| 183 |
+
"learning_rate": 3.585e-05,
|
| 184 |
+
"loss": 7.935275268554688,
|
| 185 |
+
"step": 240
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.042236864335191755,
|
| 189 |
+
"grad_norm": 0.47772353887557983,
|
| 190 |
+
"learning_rate": 3.735e-05,
|
| 191 |
+
"loss": 7.9202117919921875,
|
| 192 |
+
"step": 250
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.04392633890859943,
|
| 196 |
+
"grad_norm": 0.4412820041179657,
|
| 197 |
+
"learning_rate": 3.8849999999999996e-05,
|
| 198 |
+
"loss": 7.917314910888672,
|
| 199 |
+
"step": 260
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.0456158134820071,
|
| 203 |
+
"grad_norm": 0.49126797914505005,
|
| 204 |
+
"learning_rate": 4.035e-05,
|
| 205 |
+
"loss": 7.892892456054687,
|
| 206 |
+
"step": 270
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.047305288055414764,
|
| 210 |
+
"grad_norm": 0.41135749220848083,
|
| 211 |
+
"learning_rate": 4.185e-05,
|
| 212 |
+
"loss": 7.873385620117188,
|
| 213 |
+
"step": 280
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.048994762628822436,
|
| 217 |
+
"grad_norm": 0.3579074442386627,
|
| 218 |
+
"learning_rate": 4.334999999999999e-05,
|
| 219 |
+
"loss": 7.852500915527344,
|
| 220 |
+
"step": 290
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.05068423720223011,
|
| 224 |
+
"grad_norm": 0.47334495186805725,
|
| 225 |
+
"learning_rate": 4.484999999999999e-05,
|
| 226 |
+
"loss": 7.833164215087891,
|
| 227 |
+
"step": 300
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.05237371177563778,
|
| 231 |
+
"grad_norm": 0.5246961712837219,
|
| 232 |
+
"learning_rate": 4.6349999999999995e-05,
|
| 233 |
+
"loss": 7.8142242431640625,
|
| 234 |
+
"step": 310
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.054063186349045445,
|
| 238 |
+
"grad_norm": 0.4747469127178192,
|
| 239 |
+
"learning_rate": 4.785e-05,
|
| 240 |
+
"loss": 7.786991119384766,
|
| 241 |
+
"step": 320
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.055752660922453116,
|
| 245 |
+
"grad_norm": 0.5847325921058655,
|
| 246 |
+
"learning_rate": 4.935e-05,
|
| 247 |
+
"loss": 7.7430572509765625,
|
| 248 |
+
"step": 330
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.05744213549586079,
|
| 252 |
+
"grad_norm": 0.5468484163284302,
|
| 253 |
+
"learning_rate": 5.0849999999999996e-05,
|
| 254 |
+
"loss": 7.7266845703125,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.05913161006926846,
|
| 259 |
+
"grad_norm": 0.5309090614318848,
|
| 260 |
+
"learning_rate": 5.234999999999999e-05,
|
| 261 |
+
"loss": 7.715785217285156,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.060821084642676125,
|
| 266 |
+
"grad_norm": 0.45586320757865906,
|
| 267 |
+
"learning_rate": 5.3849999999999994e-05,
|
| 268 |
+
"loss": 7.676018524169922,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.0625105592160838,
|
| 273 |
+
"grad_norm": 0.6824954748153687,
|
| 274 |
+
"learning_rate": 5.535e-05,
|
| 275 |
+
"loss": 7.658743286132813,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.06420003378949146,
|
| 280 |
+
"grad_norm": 0.4770432710647583,
|
| 281 |
+
"learning_rate": 5.684999999999999e-05,
|
| 282 |
+
"loss": 7.6480712890625,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.06588950836289914,
|
| 287 |
+
"grad_norm": 0.4217078387737274,
|
| 288 |
+
"learning_rate": 5.8349999999999995e-05,
|
| 289 |
+
"loss": 7.612128448486328,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.0675789829363068,
|
| 294 |
+
"grad_norm": 0.6638941168785095,
|
| 295 |
+
"learning_rate": 5.985e-05,
|
| 296 |
+
"loss": 7.605058288574218,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.06926845750971448,
|
| 301 |
+
"grad_norm": 0.5383668541908264,
|
| 302 |
+
"learning_rate": 6.134999999999999e-05,
|
| 303 |
+
"loss": 7.576911926269531,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.07095793208312215,
|
| 308 |
+
"grad_norm": 0.6174895763397217,
|
| 309 |
+
"learning_rate": 6.285e-05,
|
| 310 |
+
"loss": 7.5539703369140625,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.07264740665652981,
|
| 315 |
+
"grad_norm": 0.5723831653594971,
|
| 316 |
+
"learning_rate": 6.434999999999999e-05,
|
| 317 |
+
"loss": 7.541629028320313,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.0743368812299375,
|
| 322 |
+
"grad_norm": 0.6536343693733215,
|
| 323 |
+
"learning_rate": 6.584999999999999e-05,
|
| 324 |
+
"loss": 7.522487640380859,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.07602635580334516,
|
| 329 |
+
"grad_norm": 0.654776394367218,
|
| 330 |
+
"learning_rate": 6.735e-05,
|
| 331 |
+
"loss": 7.4989463806152346,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.07771583037675282,
|
| 336 |
+
"grad_norm": 0.865844190120697,
|
| 337 |
+
"learning_rate": 6.884999999999999e-05,
|
| 338 |
+
"loss": 7.476695251464844,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.0794053049501605,
|
| 343 |
+
"grad_norm": 0.5125293731689453,
|
| 344 |
+
"learning_rate": 7.034999999999999e-05,
|
| 345 |
+
"loss": 7.4570671081542965,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.08109477952356817,
|
| 350 |
+
"grad_norm": 0.5413561463356018,
|
| 351 |
+
"learning_rate": 7.184999999999998e-05,
|
| 352 |
+
"loss": 7.443260192871094,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.08278425409697585,
|
| 357 |
+
"grad_norm": 0.5976828932762146,
|
| 358 |
+
"learning_rate": 7.335e-05,
|
| 359 |
+
"loss": 7.403485107421875,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.08447372867038351,
|
| 364 |
+
"grad_norm": 0.6476218700408936,
|
| 365 |
+
"learning_rate": 7.484999999999999e-05,
|
| 366 |
+
"loss": 7.4032142639160154,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.08447372867038351,
|
| 371 |
+
"eval_loss": 7.389806747436523,
|
| 372 |
+
"eval_runtime": 8.5684,
|
| 373 |
+
"eval_samples_per_second": 116.708,
|
| 374 |
+
"eval_steps_per_second": 2.451,
|
| 375 |
+
"step": 500
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 10,
|
| 379 |
+
"max_steps": 11838,
|
| 380 |
"num_input_tokens_seen": 0,
|
| 381 |
"num_train_epochs": 2,
|
| 382 |
"save_steps": 500,
|
|
|
|
| 387 |
"should_evaluate": false,
|
| 388 |
"should_log": false,
|
| 389 |
"should_save": true,
|
| 390 |
+
"should_training_stop": false
|
| 391 |
},
|
| 392 |
"attributes": {}
|
| 393 |
}
|
| 394 |
},
|
| 395 |
+
"total_flos": 1.6722841042944e+16,
|
| 396 |
"train_batch_size": 48,
|
| 397 |
"trial_name": null,
|
| 398 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5201
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fce02471cb82f83442a696c0b3bab66a52bc0f41341df1b015701dd7299e8f59
|
| 3 |
size 5201
|