Upload folder using huggingface_hub
Browse files- config.json +40 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +11 -0
- trainer_state.json +490 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "models/GPT2_five_function_42",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 2,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 768,
|
| 16 |
+
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 12,
|
| 19 |
+
"n_positions": 128,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"reorder_and_upcast_attn": false,
|
| 22 |
+
"resid_pdrop": 0.1,
|
| 23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 24 |
+
"scale_attn_weights": true,
|
| 25 |
+
"summary_activation": null,
|
| 26 |
+
"summary_first_dropout": 0.1,
|
| 27 |
+
"summary_proj_to_labels": true,
|
| 28 |
+
"summary_type": "cls_index",
|
| 29 |
+
"summary_use_proj": true,
|
| 30 |
+
"task_specific_params": {
|
| 31 |
+
"text-generation": {
|
| 32 |
+
"do_sample": true,
|
| 33 |
+
"max_length": 50
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.30.2",
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 32768
|
| 40 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 1,
|
| 6 |
+
"transformers_version": "4.30.2"
|
| 7 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2042058d32435903b6286712f028862be830c7995d5f2f09665001756aca518
|
| 3 |
+
size 882648587
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e27b655fc77fbc1aae783640386c91aaeb5ec8d7ea06c3bb39172d56a93708ed
|
| 3 |
+
size 441329395
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d60a56bf89d4785c4e2b3a1313f417d620bd31e4afc51342ef574701548d026
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c19057ef9645e6fc4bc707c17964cd7382788869f61e1aa0132edd8c1f6b9d98
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"token": null,
|
| 9 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 10 |
+
"unk_token": "<unk>"
|
| 11 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,490 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 3.599998950958252,
|
| 3 |
+
"best_model_checkpoint": "models/GPT2_five_function_42/checkpoint-64080",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 64080,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.16,
|
| 12 |
+
"learning_rate": 1e-05,
|
| 13 |
+
"loss": 6.9949,
|
| 14 |
+
"step": 1000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.31,
|
| 18 |
+
"learning_rate": 2e-05,
|
| 19 |
+
"loss": 5.7461,
|
| 20 |
+
"step": 2000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.47,
|
| 24 |
+
"learning_rate": 3e-05,
|
| 25 |
+
"loss": 5.4085,
|
| 26 |
+
"step": 3000
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.62,
|
| 30 |
+
"learning_rate": 4e-05,
|
| 31 |
+
"loss": 5.1434,
|
| 32 |
+
"step": 4000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.78,
|
| 36 |
+
"learning_rate": 5e-05,
|
| 37 |
+
"loss": 4.933,
|
| 38 |
+
"step": 5000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.94,
|
| 42 |
+
"learning_rate": 6e-05,
|
| 43 |
+
"loss": 4.7568,
|
| 44 |
+
"step": 6000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.0,
|
| 48 |
+
"eval_accuracy": 0.3263572316618317,
|
| 49 |
+
"eval_loss": 4.562152862548828,
|
| 50 |
+
"eval_runtime": 1.9609,
|
| 51 |
+
"eval_samples_per_second": 600.758,
|
| 52 |
+
"eval_steps_per_second": 5.1,
|
| 53 |
+
"step": 6408
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.09,
|
| 57 |
+
"learning_rate": 7e-05,
|
| 58 |
+
"loss": 4.6067,
|
| 59 |
+
"step": 7000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.25,
|
| 63 |
+
"learning_rate": 8e-05,
|
| 64 |
+
"loss": 4.4864,
|
| 65 |
+
"step": 8000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.4,
|
| 69 |
+
"learning_rate": 9e-05,
|
| 70 |
+
"loss": 4.3914,
|
| 71 |
+
"step": 9000
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.56,
|
| 75 |
+
"learning_rate": 0.0001,
|
| 76 |
+
"loss": 4.3109,
|
| 77 |
+
"step": 10000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.72,
|
| 81 |
+
"learning_rate": 9.889000000000001e-05,
|
| 82 |
+
"loss": 4.2433,
|
| 83 |
+
"step": 11000
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.87,
|
| 87 |
+
"learning_rate": 9.77788888888889e-05,
|
| 88 |
+
"loss": 4.1832,
|
| 89 |
+
"step": 12000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.0,
|
| 93 |
+
"eval_accuracy": 0.36074087937649557,
|
| 94 |
+
"eval_loss": 4.056756019592285,
|
| 95 |
+
"eval_runtime": 1.9676,
|
| 96 |
+
"eval_samples_per_second": 598.695,
|
| 97 |
+
"eval_steps_per_second": 5.082,
|
| 98 |
+
"step": 12816
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.03,
|
| 102 |
+
"learning_rate": 9.66688888888889e-05,
|
| 103 |
+
"loss": 4.1265,
|
| 104 |
+
"step": 13000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.18,
|
| 108 |
+
"learning_rate": 9.55588888888889e-05,
|
| 109 |
+
"loss": 4.0565,
|
| 110 |
+
"step": 14000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.34,
|
| 114 |
+
"learning_rate": 9.444777777777778e-05,
|
| 115 |
+
"loss": 4.0283,
|
| 116 |
+
"step": 15000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.5,
|
| 120 |
+
"learning_rate": 9.333777777777777e-05,
|
| 121 |
+
"loss": 4.0035,
|
| 122 |
+
"step": 16000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.65,
|
| 126 |
+
"learning_rate": 9.222666666666668e-05,
|
| 127 |
+
"loss": 3.9768,
|
| 128 |
+
"step": 17000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.81,
|
| 132 |
+
"learning_rate": 9.111666666666667e-05,
|
| 133 |
+
"loss": 3.9553,
|
| 134 |
+
"step": 18000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.97,
|
| 138 |
+
"learning_rate": 9.000555555555557e-05,
|
| 139 |
+
"loss": 3.9365,
|
| 140 |
+
"step": 19000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 3.0,
|
| 144 |
+
"eval_accuracy": 0.3769100169779287,
|
| 145 |
+
"eval_loss": 3.874519109725952,
|
| 146 |
+
"eval_runtime": 1.9728,
|
| 147 |
+
"eval_samples_per_second": 597.128,
|
| 148 |
+
"eval_steps_per_second": 5.069,
|
| 149 |
+
"step": 19224
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 3.12,
|
| 153 |
+
"learning_rate": 8.889555555555556e-05,
|
| 154 |
+
"loss": 3.871,
|
| 155 |
+
"step": 20000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 3.28,
|
| 159 |
+
"learning_rate": 8.778444444444445e-05,
|
| 160 |
+
"loss": 3.8532,
|
| 161 |
+
"step": 21000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 3.43,
|
| 165 |
+
"learning_rate": 8.667444444444444e-05,
|
| 166 |
+
"loss": 3.8443,
|
| 167 |
+
"step": 22000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 3.59,
|
| 171 |
+
"learning_rate": 8.556444444444445e-05,
|
| 172 |
+
"loss": 3.8378,
|
| 173 |
+
"step": 23000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.75,
|
| 177 |
+
"learning_rate": 8.445333333333333e-05,
|
| 178 |
+
"loss": 3.825,
|
| 179 |
+
"step": 24000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 3.9,
|
| 183 |
+
"learning_rate": 8.334222222222222e-05,
|
| 184 |
+
"loss": 3.8154,
|
| 185 |
+
"step": 25000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 4.0,
|
| 189 |
+
"eval_accuracy": 0.3853922971003837,
|
| 190 |
+
"eval_loss": 3.779280185699463,
|
| 191 |
+
"eval_runtime": 1.9858,
|
| 192 |
+
"eval_samples_per_second": 593.214,
|
| 193 |
+
"eval_steps_per_second": 5.036,
|
| 194 |
+
"step": 25632
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.06,
|
| 198 |
+
"learning_rate": 8.223111111111111e-05,
|
| 199 |
+
"loss": 3.7779,
|
| 200 |
+
"step": 26000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.21,
|
| 204 |
+
"learning_rate": 8.112111111111111e-05,
|
| 205 |
+
"loss": 3.7386,
|
| 206 |
+
"step": 27000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 4.37,
|
| 210 |
+
"learning_rate": 8.001e-05,
|
| 211 |
+
"loss": 3.7408,
|
| 212 |
+
"step": 28000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.53,
|
| 216 |
+
"learning_rate": 7.890000000000001e-05,
|
| 217 |
+
"loss": 3.7369,
|
| 218 |
+
"step": 29000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 4.68,
|
| 222 |
+
"learning_rate": 7.77888888888889e-05,
|
| 223 |
+
"loss": 3.7354,
|
| 224 |
+
"step": 30000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 4.84,
|
| 228 |
+
"learning_rate": 7.667888888888889e-05,
|
| 229 |
+
"loss": 3.7297,
|
| 230 |
+
"step": 31000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 4.99,
|
| 234 |
+
"learning_rate": 7.556777777777779e-05,
|
| 235 |
+
"loss": 3.725,
|
| 236 |
+
"step": 32000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 5.0,
|
| 240 |
+
"eval_accuracy": 0.3909669398286165,
|
| 241 |
+
"eval_loss": 3.7228105068206787,
|
| 242 |
+
"eval_runtime": 2.0428,
|
| 243 |
+
"eval_samples_per_second": 576.664,
|
| 244 |
+
"eval_steps_per_second": 4.895,
|
| 245 |
+
"step": 32040
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 5.15,
|
| 249 |
+
"learning_rate": 7.445777777777778e-05,
|
| 250 |
+
"loss": 3.6547,
|
| 251 |
+
"step": 33000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 5.31,
|
| 255 |
+
"learning_rate": 7.334666666666668e-05,
|
| 256 |
+
"loss": 3.6602,
|
| 257 |
+
"step": 34000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 5.46,
|
| 261 |
+
"learning_rate": 7.223666666666667e-05,
|
| 262 |
+
"loss": 3.6624,
|
| 263 |
+
"step": 35000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 5.62,
|
| 267 |
+
"learning_rate": 7.112555555555556e-05,
|
| 268 |
+
"loss": 3.6649,
|
| 269 |
+
"step": 36000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 5.77,
|
| 273 |
+
"learning_rate": 7.001555555555555e-05,
|
| 274 |
+
"loss": 3.6615,
|
| 275 |
+
"step": 37000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 5.93,
|
| 279 |
+
"learning_rate": 6.890444444444445e-05,
|
| 280 |
+
"loss": 3.6621,
|
| 281 |
+
"step": 38000
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 6.0,
|
| 285 |
+
"eval_accuracy": 0.39523147467347564,
|
| 286 |
+
"eval_loss": 3.681443691253662,
|
| 287 |
+
"eval_runtime": 1.9586,
|
| 288 |
+
"eval_samples_per_second": 601.465,
|
| 289 |
+
"eval_steps_per_second": 5.106,
|
| 290 |
+
"step": 38448
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 6.09,
|
| 294 |
+
"learning_rate": 6.779444444444444e-05,
|
| 295 |
+
"loss": 3.6176,
|
| 296 |
+
"step": 39000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 6.24,
|
| 300 |
+
"learning_rate": 6.668333333333333e-05,
|
| 301 |
+
"loss": 3.5948,
|
| 302 |
+
"step": 40000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.4,
|
| 306 |
+
"learning_rate": 6.557333333333332e-05,
|
| 307 |
+
"loss": 3.6021,
|
| 308 |
+
"step": 41000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 6.55,
|
| 312 |
+
"learning_rate": 6.446222222222223e-05,
|
| 313 |
+
"loss": 3.6043,
|
| 314 |
+
"step": 42000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 6.71,
|
| 318 |
+
"learning_rate": 6.335222222222222e-05,
|
| 319 |
+
"loss": 3.6064,
|
| 320 |
+
"step": 43000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 6.87,
|
| 324 |
+
"learning_rate": 6.224111111111112e-05,
|
| 325 |
+
"loss": 3.6072,
|
| 326 |
+
"step": 44000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 7.0,
|
| 330 |
+
"eval_accuracy": 0.39868721842706845,
|
| 331 |
+
"eval_loss": 3.6536548137664795,
|
| 332 |
+
"eval_runtime": 1.9678,
|
| 333 |
+
"eval_samples_per_second": 598.633,
|
| 334 |
+
"eval_steps_per_second": 5.082,
|
| 335 |
+
"step": 44856
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 7.02,
|
| 339 |
+
"learning_rate": 6.113111111111111e-05,
|
| 340 |
+
"loss": 3.5958,
|
| 341 |
+
"step": 45000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 7.18,
|
| 345 |
+
"learning_rate": 6.002e-05,
|
| 346 |
+
"loss": 3.5371,
|
| 347 |
+
"step": 46000
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 7.33,
|
| 351 |
+
"learning_rate": 5.891e-05,
|
| 352 |
+
"loss": 3.5493,
|
| 353 |
+
"step": 47000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 7.49,
|
| 357 |
+
"learning_rate": 5.779888888888889e-05,
|
| 358 |
+
"loss": 3.554,
|
| 359 |
+
"step": 48000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 7.65,
|
| 363 |
+
"learning_rate": 5.668888888888889e-05,
|
| 364 |
+
"loss": 3.5593,
|
| 365 |
+
"step": 49000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 7.8,
|
| 369 |
+
"learning_rate": 5.5577777777777784e-05,
|
| 370 |
+
"loss": 3.5597,
|
| 371 |
+
"step": 50000
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 7.96,
|
| 375 |
+
"learning_rate": 5.446777777777778e-05,
|
| 376 |
+
"loss": 3.5598,
|
| 377 |
+
"step": 51000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 8.0,
|
| 381 |
+
"eval_accuracy": 0.4002713794901274,
|
| 382 |
+
"eval_loss": 3.631843328475952,
|
| 383 |
+
"eval_runtime": 1.9682,
|
| 384 |
+
"eval_samples_per_second": 598.504,
|
| 385 |
+
"eval_steps_per_second": 5.081,
|
| 386 |
+
"step": 51264
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 8.11,
|
| 390 |
+
"learning_rate": 5.3356666666666663e-05,
|
| 391 |
+
"loss": 3.5064,
|
| 392 |
+
"step": 52000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 8.27,
|
| 396 |
+
"learning_rate": 5.224666666666667e-05,
|
| 397 |
+
"loss": 3.5007,
|
| 398 |
+
"step": 53000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 8.43,
|
| 402 |
+
"learning_rate": 5.1135555555555556e-05,
|
| 403 |
+
"loss": 3.511,
|
| 404 |
+
"step": 54000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 8.58,
|
| 408 |
+
"learning_rate": 5.002555555555556e-05,
|
| 409 |
+
"loss": 3.5135,
|
| 410 |
+
"step": 55000
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 8.74,
|
| 414 |
+
"learning_rate": 4.891444444444444e-05,
|
| 415 |
+
"loss": 3.5193,
|
| 416 |
+
"step": 56000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 8.9,
|
| 420 |
+
"learning_rate": 4.780444444444445e-05,
|
| 421 |
+
"loss": 3.5203,
|
| 422 |
+
"step": 57000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 9.0,
|
| 426 |
+
"eval_accuracy": 0.4027378581072952,
|
| 427 |
+
"eval_loss": 3.6141819953918457,
|
| 428 |
+
"eval_runtime": 1.9786,
|
| 429 |
+
"eval_samples_per_second": 595.365,
|
| 430 |
+
"eval_steps_per_second": 5.054,
|
| 431 |
+
"step": 57672
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 9.05,
|
| 435 |
+
"learning_rate": 4.6693333333333336e-05,
|
| 436 |
+
"loss": 3.4957,
|
| 437 |
+
"step": 58000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 9.21,
|
| 441 |
+
"learning_rate": 4.5583333333333335e-05,
|
| 442 |
+
"loss": 3.4579,
|
| 443 |
+
"step": 59000
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 9.36,
|
| 447 |
+
"learning_rate": 4.447222222222223e-05,
|
| 448 |
+
"loss": 3.4682,
|
| 449 |
+
"step": 60000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 9.52,
|
| 453 |
+
"learning_rate": 4.336222222222223e-05,
|
| 454 |
+
"loss": 3.4743,
|
| 455 |
+
"step": 61000
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 9.68,
|
| 459 |
+
"learning_rate": 4.2251111111111115e-05,
|
| 460 |
+
"loss": 3.4784,
|
| 461 |
+
"step": 62000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 9.83,
|
| 465 |
+
"learning_rate": 4.1141111111111114e-05,
|
| 466 |
+
"loss": 3.4833,
|
| 467 |
+
"step": 63000
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 9.99,
|
| 471 |
+
"learning_rate": 4.003e-05,
|
| 472 |
+
"loss": 3.4839,
|
| 473 |
+
"step": 64000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 10.0,
|
| 477 |
+
"eval_accuracy": 0.40503723112709383,
|
| 478 |
+
"eval_loss": 3.599998950958252,
|
| 479 |
+
"eval_runtime": 1.9622,
|
| 480 |
+
"eval_samples_per_second": 600.357,
|
| 481 |
+
"eval_steps_per_second": 5.096,
|
| 482 |
+
"step": 64080
|
| 483 |
+
}
|
| 484 |
+
],
|
| 485 |
+
"max_steps": 100000,
|
| 486 |
+
"num_train_epochs": 16,
|
| 487 |
+
"total_flos": 5.3573097259008e+17,
|
| 488 |
+
"trial_name": null,
|
| 489 |
+
"trial_params": null
|
| 490 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85121e6559a4fb193940028a4bbc7d8a884d8aeaa139c9b1b1e5866e00361517
|
| 3 |
+
size 4881
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|