Upload folder using huggingface_hub
Browse files- config.json +55 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +22 -0
- trainer_state.json +306 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "EleutherAI/gpt-neo-125m",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPTNeoForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0,
|
| 8 |
+
"attention_layers": [
|
| 9 |
+
"global",
|
| 10 |
+
"local",
|
| 11 |
+
"global",
|
| 12 |
+
"local",
|
| 13 |
+
"global",
|
| 14 |
+
"local",
|
| 15 |
+
"global",
|
| 16 |
+
"local",
|
| 17 |
+
"global",
|
| 18 |
+
"local",
|
| 19 |
+
"global",
|
| 20 |
+
"local"
|
| 21 |
+
],
|
| 22 |
+
"attention_types": [
|
| 23 |
+
[
|
| 24 |
+
[
|
| 25 |
+
"global",
|
| 26 |
+
"local"
|
| 27 |
+
],
|
| 28 |
+
6
|
| 29 |
+
]
|
| 30 |
+
],
|
| 31 |
+
"bos_token_id": 50256,
|
| 32 |
+
"classifier_dropout": 0.1,
|
| 33 |
+
"embed_dropout": 0,
|
| 34 |
+
"eos_token_id": 50256,
|
| 35 |
+
"gradient_checkpointing": false,
|
| 36 |
+
"hidden_size": 768,
|
| 37 |
+
"initializer_range": 0.02,
|
| 38 |
+
"intermediate_size": null,
|
| 39 |
+
"layer_norm_epsilon": 1e-05,
|
| 40 |
+
"max_position_embeddings": 2048,
|
| 41 |
+
"model_type": "gpt_neo",
|
| 42 |
+
"num_heads": 12,
|
| 43 |
+
"num_layers": 12,
|
| 44 |
+
"resid_dropout": 0,
|
| 45 |
+
"summary_activation": null,
|
| 46 |
+
"summary_first_dropout": 0.1,
|
| 47 |
+
"summary_proj_to_labels": true,
|
| 48 |
+
"summary_type": "cls_index",
|
| 49 |
+
"summary_use_proj": true,
|
| 50 |
+
"torch_dtype": "float32",
|
| 51 |
+
"transformers_version": "4.41.1",
|
| 52 |
+
"use_cache": true,
|
| 53 |
+
"vocab_size": 50257,
|
| 54 |
+
"window_size": 256
|
| 55 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.41.1"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e58384c39f6b57840064722e855a960d063b76f3a64cebb2ee33931df17c260c
|
| 3 |
+
size 500811336
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:013a4d3633195d0d03ee87e59ccf070a4a8a8f9970d1529cfefcce69d9cf39b6
|
| 3 |
+
size 1001722938
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3eb5380b51c188533b1d18890b787cfed18b13de4c78578f31e2419b1d626032
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
},
|
| 14 |
+
"bos_token": "<|endoftext|>",
|
| 15 |
+
"clean_up_tokenization_spaces": true,
|
| 16 |
+
"eos_token": "<|endoftext|>",
|
| 17 |
+
"errors": "replace",
|
| 18 |
+
"model_max_length": 2048,
|
| 19 |
+
"pad_token": "<|endoftext|>",
|
| 20 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 21 |
+
"unk_token": "<|endoftext|>"
|
| 22 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,306 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.1642619311875695,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 19500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05549389567147614,
|
| 13 |
+
"grad_norm": 5.1054205894470215,
|
| 14 |
+
"learning_rate": 0.0009815020347761745,
|
| 15 |
+
"loss": 2.823,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.11098779134295228,
|
| 20 |
+
"grad_norm": 5.702259540557861,
|
| 21 |
+
"learning_rate": 0.0009630040695523493,
|
| 22 |
+
"loss": 2.5297,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.16648168701442842,
|
| 27 |
+
"grad_norm": 2.288583278656006,
|
| 28 |
+
"learning_rate": 0.0009445061043285239,
|
| 29 |
+
"loss": 2.2922,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.22197558268590456,
|
| 34 |
+
"grad_norm": 1.2640436887741089,
|
| 35 |
+
"learning_rate": 0.0009260081391046985,
|
| 36 |
+
"loss": 2.2693,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.27746947835738067,
|
| 41 |
+
"grad_norm": 2.6587376594543457,
|
| 42 |
+
"learning_rate": 0.0009075101738808731,
|
| 43 |
+
"loss": 2.1495,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.33296337402885684,
|
| 48 |
+
"grad_norm": 3.5381200313568115,
|
| 49 |
+
"learning_rate": 0.0008890122086570478,
|
| 50 |
+
"loss": 2.0572,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.38845726970033295,
|
| 55 |
+
"grad_norm": 5.533036708831787,
|
| 56 |
+
"learning_rate": 0.0008705142434332224,
|
| 57 |
+
"loss": 2.0025,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4439511653718091,
|
| 62 |
+
"grad_norm": 5.4949541091918945,
|
| 63 |
+
"learning_rate": 0.000852016278209397,
|
| 64 |
+
"loss": 1.9598,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.49944506104328523,
|
| 69 |
+
"grad_norm": 1.909883737564087,
|
| 70 |
+
"learning_rate": 0.0008335183129855716,
|
| 71 |
+
"loss": 1.9381,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5549389567147613,
|
| 76 |
+
"grad_norm": 5.691808223724365,
|
| 77 |
+
"learning_rate": 0.0008150203477617462,
|
| 78 |
+
"loss": 1.8509,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.6104328523862376,
|
| 83 |
+
"grad_norm": 2.442469358444214,
|
| 84 |
+
"learning_rate": 0.0007965223825379209,
|
| 85 |
+
"loss": 1.7988,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6659267480577137,
|
| 90 |
+
"grad_norm": 2.9826149940490723,
|
| 91 |
+
"learning_rate": 0.0007780244173140955,
|
| 92 |
+
"loss": 1.7816,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.7214206437291898,
|
| 97 |
+
"grad_norm": 2.3049557209014893,
|
| 98 |
+
"learning_rate": 0.00075952645209027,
|
| 99 |
+
"loss": 1.7736,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7769145394006659,
|
| 104 |
+
"grad_norm": 2.855045795440674,
|
| 105 |
+
"learning_rate": 0.0007410284868664448,
|
| 106 |
+
"loss": 1.7075,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.832408435072142,
|
| 111 |
+
"grad_norm": 3.2882728576660156,
|
| 112 |
+
"learning_rate": 0.0007225305216426194,
|
| 113 |
+
"loss": 1.701,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.8879023307436182,
|
| 118 |
+
"grad_norm": 2.1633858680725098,
|
| 119 |
+
"learning_rate": 0.0007040325564187939,
|
| 120 |
+
"loss": 1.6848,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.9433962264150944,
|
| 125 |
+
"grad_norm": 2.723276138305664,
|
| 126 |
+
"learning_rate": 0.0006855345911949685,
|
| 127 |
+
"loss": 1.6152,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.9988901220865705,
|
| 132 |
+
"grad_norm": 2.73237943649292,
|
| 133 |
+
"learning_rate": 0.0006670366259711433,
|
| 134 |
+
"loss": 1.5959,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.0543840177580466,
|
| 139 |
+
"grad_norm": 2.634521007537842,
|
| 140 |
+
"learning_rate": 0.0006485386607473178,
|
| 141 |
+
"loss": 1.4009,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.1098779134295227,
|
| 146 |
+
"grad_norm": 1.5136901140213013,
|
| 147 |
+
"learning_rate": 0.0006300406955234924,
|
| 148 |
+
"loss": 1.3877,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.1653718091009988,
|
| 153 |
+
"grad_norm": 2.1514732837677,
|
| 154 |
+
"learning_rate": 0.000611542730299667,
|
| 155 |
+
"loss": 1.3724,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.220865704772475,
|
| 160 |
+
"grad_norm": 2.6399548053741455,
|
| 161 |
+
"learning_rate": 0.0005930447650758417,
|
| 162 |
+
"loss": 1.335,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.2763596004439512,
|
| 167 |
+
"grad_norm": 1.5254985094070435,
|
| 168 |
+
"learning_rate": 0.0005745467998520163,
|
| 169 |
+
"loss": 1.3886,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.3318534961154274,
|
| 174 |
+
"grad_norm": 1.9089288711547852,
|
| 175 |
+
"learning_rate": 0.0005560488346281908,
|
| 176 |
+
"loss": 1.3439,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.3873473917869035,
|
| 181 |
+
"grad_norm": 2.2264904975891113,
|
| 182 |
+
"learning_rate": 0.0005375508694043655,
|
| 183 |
+
"loss": 1.3081,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.4428412874583796,
|
| 188 |
+
"grad_norm": 2.0363707542419434,
|
| 189 |
+
"learning_rate": 0.0005190529041805402,
|
| 190 |
+
"loss": 1.3539,
|
| 191 |
+
"step": 13000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.4983351831298557,
|
| 195 |
+
"grad_norm": 1.3880550861358643,
|
| 196 |
+
"learning_rate": 0.0005005549389567147,
|
| 197 |
+
"loss": 1.3054,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.5538290788013318,
|
| 202 |
+
"grad_norm": 1.9909353256225586,
|
| 203 |
+
"learning_rate": 0.00048205697373288937,
|
| 204 |
+
"loss": 1.2664,
|
| 205 |
+
"step": 14000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.609322974472808,
|
| 209 |
+
"grad_norm": 1.8012514114379883,
|
| 210 |
+
"learning_rate": 0.000463559008509064,
|
| 211 |
+
"loss": 1.3344,
|
| 212 |
+
"step": 14500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.6648168701442843,
|
| 216 |
+
"grad_norm": 1.5090456008911133,
|
| 217 |
+
"learning_rate": 0.00044506104328523863,
|
| 218 |
+
"loss": 1.3274,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.7203107658157601,
|
| 223 |
+
"grad_norm": 2.566316843032837,
|
| 224 |
+
"learning_rate": 0.00042656307806141327,
|
| 225 |
+
"loss": 1.2629,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.7758046614872365,
|
| 230 |
+
"grad_norm": 1.7907458543777466,
|
| 231 |
+
"learning_rate": 0.00040806511283758784,
|
| 232 |
+
"loss": 1.3041,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.8312985571587126,
|
| 237 |
+
"grad_norm": 1.4483698606491089,
|
| 238 |
+
"learning_rate": 0.0003895671476137625,
|
| 239 |
+
"loss": 1.2407,
|
| 240 |
+
"step": 16500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.8867924528301887,
|
| 244 |
+
"grad_norm": 2.474891424179077,
|
| 245 |
+
"learning_rate": 0.0003710691823899371,
|
| 246 |
+
"loss": 1.2555,
|
| 247 |
+
"step": 17000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.9422863485016648,
|
| 251 |
+
"grad_norm": 1.0690557956695557,
|
| 252 |
+
"learning_rate": 0.00035257121716611174,
|
| 253 |
+
"loss": 1.2407,
|
| 254 |
+
"step": 17500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.997780244173141,
|
| 258 |
+
"grad_norm": 1.2744386196136475,
|
| 259 |
+
"learning_rate": 0.00033407325194228637,
|
| 260 |
+
"loss": 1.1843,
|
| 261 |
+
"step": 18000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.0532741398446173,
|
| 265 |
+
"grad_norm": 0.9873028993606567,
|
| 266 |
+
"learning_rate": 0.000315575286718461,
|
| 267 |
+
"loss": 0.9438,
|
| 268 |
+
"step": 18500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 2.108768035516093,
|
| 272 |
+
"grad_norm": 3.0536534786224365,
|
| 273 |
+
"learning_rate": 0.00029707732149463563,
|
| 274 |
+
"loss": 0.918,
|
| 275 |
+
"step": 19000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.1642619311875695,
|
| 279 |
+
"grad_norm": 1.4433006048202515,
|
| 280 |
+
"learning_rate": 0.0002785793562708102,
|
| 281 |
+
"loss": 0.9162,
|
| 282 |
+
"step": 19500
|
| 283 |
+
}
|
| 284 |
+
],
|
| 285 |
+
"logging_steps": 500,
|
| 286 |
+
"max_steps": 27030,
|
| 287 |
+
"num_input_tokens_seen": 0,
|
| 288 |
+
"num_train_epochs": 3,
|
| 289 |
+
"save_steps": 500,
|
| 290 |
+
"stateful_callbacks": {
|
| 291 |
+
"TrainerControl": {
|
| 292 |
+
"args": {
|
| 293 |
+
"should_epoch_stop": false,
|
| 294 |
+
"should_evaluate": false,
|
| 295 |
+
"should_log": false,
|
| 296 |
+
"should_save": true,
|
| 297 |
+
"should_training_stop": false
|
| 298 |
+
},
|
| 299 |
+
"attributes": {}
|
| 300 |
+
}
|
| 301 |
+
},
|
| 302 |
+
"total_flos": 4.074621752888525e+16,
|
| 303 |
+
"train_batch_size": 2,
|
| 304 |
+
"trial_name": null,
|
| 305 |
+
"trial_params": null
|
| 306 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:559ebe37b6357d265519108be281de7623be6372238b3a7771e939e2c28a9150
|
| 3 |
+
size 5112
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|