Upload folder using huggingface_hub
Browse files- checkpoint-1080/config.json +39 -0
- checkpoint-1080/generation_config.json +6 -0
- checkpoint-1080/model.safetensors +3 -0
- checkpoint-1080/optimizer.pt +3 -0
- checkpoint-1080/rng_state.pth +3 -0
- checkpoint-1080/scheduler.pt +3 -0
- checkpoint-1080/trainer_state.json +633 -0
- checkpoint-1080/training_args.bin +3 -0
- config.json +39 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +23 -0
- tokenizer_config.json +22 -0
- vocab.json +0 -0
checkpoint-1080/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 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": 1024,
|
| 20 |
+
"reorder_and_upcast_attn": false,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.41.2",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50257
|
| 39 |
+
}
|
checkpoint-1080/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": "4.41.2"
|
| 6 |
+
}
|
checkpoint-1080/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8d22586f32398abba71287fc9fbd27f68a106fb4da5a21da85e439f4ea68d69
|
| 3 |
+
size 497774208
|
checkpoint-1080/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8edcb57babe79aa1e063b9c16387aa7ebed4e6897e63f0b3c4ba6ad1a9a1612f
|
| 3 |
+
size 995642298
|
checkpoint-1080/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79779268804a95867176b02165dcf4317af5dbf20937682f497d224c91733bf4
|
| 3 |
+
size 14244
|
checkpoint-1080/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:143a5b3812f11a0ce92f4896d57f598a2f196c87d5b52f7101c582a4b86122c2
|
| 3 |
+
size 1064
|
checkpoint-1080/trainer_state.json
ADDED
|
@@ -0,0 +1,633 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1080,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 6.0880818367004395,
|
| 14 |
+
"learning_rate": 3.6e-05,
|
| 15 |
+
"loss": 3.2849,
|
| 16 |
+
"step": 36
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.010123239436619719,
|
| 21 |
+
"eval_bleu": 0.10518697359828132,
|
| 22 |
+
"eval_f1": 0.010153581748448041,
|
| 23 |
+
"eval_loss": 2.6219797134399414,
|
| 24 |
+
"eval_precision": 0.010202794685557478,
|
| 25 |
+
"eval_recall": 0.010123239436619719,
|
| 26 |
+
"eval_runtime": 6.2453,
|
| 27 |
+
"eval_samples_per_second": 22.737,
|
| 28 |
+
"eval_steps_per_second": 2.882,
|
| 29 |
+
"step": 36
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"grad_norm": 6.915263652801514,
|
| 34 |
+
"learning_rate": 4.893203883495146e-05,
|
| 35 |
+
"loss": 2.2637,
|
| 36 |
+
"step": 72
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_accuracy": 0.01248899647887324,
|
| 41 |
+
"eval_bleu": 0.13792868891001447,
|
| 42 |
+
"eval_f1": 0.010680838430589857,
|
| 43 |
+
"eval_loss": 2.017970561981201,
|
| 44 |
+
"eval_precision": 0.009509030569956453,
|
| 45 |
+
"eval_recall": 0.012488996478873238,
|
| 46 |
+
"eval_runtime": 7.0653,
|
| 47 |
+
"eval_samples_per_second": 20.098,
|
| 48 |
+
"eval_steps_per_second": 2.548,
|
| 49 |
+
"step": 72
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 3.0,
|
| 53 |
+
"grad_norm": 7.544444561004639,
|
| 54 |
+
"learning_rate": 4.718446601941748e-05,
|
| 55 |
+
"loss": 1.789,
|
| 56 |
+
"step": 108
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.0,
|
| 60 |
+
"eval_accuracy": 0.012654049295774648,
|
| 61 |
+
"eval_bleu": 0.17566093139607744,
|
| 62 |
+
"eval_f1": 0.011466852239797607,
|
| 63 |
+
"eval_loss": 1.7966645956039429,
|
| 64 |
+
"eval_precision": 0.01049697288064746,
|
| 65 |
+
"eval_recall": 0.012654049295774647,
|
| 66 |
+
"eval_runtime": 6.0435,
|
| 67 |
+
"eval_samples_per_second": 23.496,
|
| 68 |
+
"eval_steps_per_second": 2.978,
|
| 69 |
+
"step": 108
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.0,
|
| 73 |
+
"grad_norm": 6.955804347991943,
|
| 74 |
+
"learning_rate": 4.543689320388349e-05,
|
| 75 |
+
"loss": 1.5522,
|
| 76 |
+
"step": 144
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 4.0,
|
| 80 |
+
"eval_accuracy": 0.012378961267605635,
|
| 81 |
+
"eval_bleu": 0.20413318737157596,
|
| 82 |
+
"eval_f1": 0.011132478900133054,
|
| 83 |
+
"eval_loss": 1.6657302379608154,
|
| 84 |
+
"eval_precision": 0.010120661403149588,
|
| 85 |
+
"eval_recall": 0.012378961267605633,
|
| 86 |
+
"eval_runtime": 6.1905,
|
| 87 |
+
"eval_samples_per_second": 22.938,
|
| 88 |
+
"eval_steps_per_second": 2.908,
|
| 89 |
+
"step": 144
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.0,
|
| 93 |
+
"grad_norm": 7.229798793792725,
|
| 94 |
+
"learning_rate": 4.368932038834951e-05,
|
| 95 |
+
"loss": 1.3885,
|
| 96 |
+
"step": 180
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.0,
|
| 100 |
+
"eval_accuracy": 0.012378961267605635,
|
| 101 |
+
"eval_bleu": 0.2305940937780942,
|
| 102 |
+
"eval_f1": 0.011073979352246164,
|
| 103 |
+
"eval_loss": 1.5827170610427856,
|
| 104 |
+
"eval_precision": 0.010022195626080541,
|
| 105 |
+
"eval_recall": 0.012378961267605633,
|
| 106 |
+
"eval_runtime": 6.9109,
|
| 107 |
+
"eval_samples_per_second": 20.547,
|
| 108 |
+
"eval_steps_per_second": 2.605,
|
| 109 |
+
"step": 180
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 6.0,
|
| 113 |
+
"grad_norm": 6.714682102203369,
|
| 114 |
+
"learning_rate": 4.194174757281554e-05,
|
| 115 |
+
"loss": 1.2561,
|
| 116 |
+
"step": 216
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 6.0,
|
| 120 |
+
"eval_accuracy": 0.012268926056338027,
|
| 121 |
+
"eval_bleu": 0.25012821385731565,
|
| 122 |
+
"eval_f1": 0.01143102719262594,
|
| 123 |
+
"eval_loss": 1.5294432640075684,
|
| 124 |
+
"eval_precision": 0.010707247710344536,
|
| 125 |
+
"eval_recall": 0.012268926056338027,
|
| 126 |
+
"eval_runtime": 6.5697,
|
| 127 |
+
"eval_samples_per_second": 21.614,
|
| 128 |
+
"eval_steps_per_second": 2.74,
|
| 129 |
+
"step": 216
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 7.0,
|
| 133 |
+
"grad_norm": 6.063908100128174,
|
| 134 |
+
"learning_rate": 4.019417475728156e-05,
|
| 135 |
+
"loss": 1.1466,
|
| 136 |
+
"step": 252
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 7.0,
|
| 140 |
+
"eval_accuracy": 0.012268926056338027,
|
| 141 |
+
"eval_bleu": 0.2719546447213355,
|
| 142 |
+
"eval_f1": 0.01116903184495446,
|
| 143 |
+
"eval_loss": 1.4926397800445557,
|
| 144 |
+
"eval_precision": 0.010253161244814542,
|
| 145 |
+
"eval_recall": 0.012268926056338027,
|
| 146 |
+
"eval_runtime": 6.4161,
|
| 147 |
+
"eval_samples_per_second": 22.132,
|
| 148 |
+
"eval_steps_per_second": 2.805,
|
| 149 |
+
"step": 252
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"grad_norm": 6.155008316040039,
|
| 154 |
+
"learning_rate": 3.844660194174757e-05,
|
| 155 |
+
"loss": 1.0616,
|
| 156 |
+
"step": 288
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 8.0,
|
| 160 |
+
"eval_accuracy": 0.012378961267605635,
|
| 161 |
+
"eval_bleu": 0.28742380325292655,
|
| 162 |
+
"eval_f1": 0.01144092667248244,
|
| 163 |
+
"eval_loss": 1.4650629758834839,
|
| 164 |
+
"eval_precision": 0.010640060069611993,
|
| 165 |
+
"eval_recall": 0.012378961267605633,
|
| 166 |
+
"eval_runtime": 6.3235,
|
| 167 |
+
"eval_samples_per_second": 22.456,
|
| 168 |
+
"eval_steps_per_second": 2.847,
|
| 169 |
+
"step": 288
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 9.0,
|
| 173 |
+
"grad_norm": 5.874176979064941,
|
| 174 |
+
"learning_rate": 3.6699029126213596e-05,
|
| 175 |
+
"loss": 0.9821,
|
| 176 |
+
"step": 324
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 9.0,
|
| 180 |
+
"eval_accuracy": 0.012268926056338027,
|
| 181 |
+
"eval_bleu": 0.30478814512361185,
|
| 182 |
+
"eval_f1": 0.011331946253740536,
|
| 183 |
+
"eval_loss": 1.4492626190185547,
|
| 184 |
+
"eval_precision": 0.010531151474565863,
|
| 185 |
+
"eval_recall": 0.012268926056338027,
|
| 186 |
+
"eval_runtime": 6.2565,
|
| 187 |
+
"eval_samples_per_second": 22.696,
|
| 188 |
+
"eval_steps_per_second": 2.877,
|
| 189 |
+
"step": 324
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 10.0,
|
| 193 |
+
"grad_norm": 5.705406665802002,
|
| 194 |
+
"learning_rate": 3.4951456310679615e-05,
|
| 195 |
+
"loss": 0.9071,
|
| 196 |
+
"step": 360
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 10.0,
|
| 200 |
+
"eval_accuracy": 0.012268926056338027,
|
| 201 |
+
"eval_bleu": 0.3250108739654091,
|
| 202 |
+
"eval_f1": 0.011214281037053235,
|
| 203 |
+
"eval_loss": 1.4369895458221436,
|
| 204 |
+
"eval_precision": 0.010327542425543311,
|
| 205 |
+
"eval_recall": 0.012268926056338027,
|
| 206 |
+
"eval_runtime": 6.1165,
|
| 207 |
+
"eval_samples_per_second": 23.216,
|
| 208 |
+
"eval_steps_per_second": 2.943,
|
| 209 |
+
"step": 360
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 11.0,
|
| 213 |
+
"grad_norm": 5.345541000366211,
|
| 214 |
+
"learning_rate": 3.3203883495145634e-05,
|
| 215 |
+
"loss": 0.8445,
|
| 216 |
+
"step": 396
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 11.0,
|
| 220 |
+
"eval_accuracy": 0.012268926056338027,
|
| 221 |
+
"eval_bleu": 0.32825465058506376,
|
| 222 |
+
"eval_f1": 0.011419929314754076,
|
| 223 |
+
"eval_loss": 1.4337056875228882,
|
| 224 |
+
"eval_precision": 0.010683679060359908,
|
| 225 |
+
"eval_recall": 0.012268926056338027,
|
| 226 |
+
"eval_runtime": 6.9862,
|
| 227 |
+
"eval_samples_per_second": 20.326,
|
| 228 |
+
"eval_steps_per_second": 2.577,
|
| 229 |
+
"step": 396
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 12.0,
|
| 233 |
+
"grad_norm": 4.928064346313477,
|
| 234 |
+
"learning_rate": 3.145631067961165e-05,
|
| 235 |
+
"loss": 0.7869,
|
| 236 |
+
"step": 432
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 12.0,
|
| 240 |
+
"eval_accuracy": 0.012268926056338027,
|
| 241 |
+
"eval_bleu": 0.34315751189373966,
|
| 242 |
+
"eval_f1": 0.011425905613358798,
|
| 243 |
+
"eval_loss": 1.431230902671814,
|
| 244 |
+
"eval_precision": 0.010692912514740159,
|
| 245 |
+
"eval_recall": 0.012268926056338027,
|
| 246 |
+
"eval_runtime": 6.3375,
|
| 247 |
+
"eval_samples_per_second": 22.406,
|
| 248 |
+
"eval_steps_per_second": 2.84,
|
| 249 |
+
"step": 432
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 13.0,
|
| 253 |
+
"grad_norm": 4.787758827209473,
|
| 254 |
+
"learning_rate": 2.9708737864077673e-05,
|
| 255 |
+
"loss": 0.7388,
|
| 256 |
+
"step": 468
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 13.0,
|
| 260 |
+
"eval_accuracy": 0.012268926056338027,
|
| 261 |
+
"eval_bleu": 0.3506530097105922,
|
| 262 |
+
"eval_f1": 0.011567695105672023,
|
| 263 |
+
"eval_loss": 1.432782530784607,
|
| 264 |
+
"eval_precision": 0.010942929955906473,
|
| 265 |
+
"eval_recall": 0.012268926056338027,
|
| 266 |
+
"eval_runtime": 6.6203,
|
| 267 |
+
"eval_samples_per_second": 21.449,
|
| 268 |
+
"eval_steps_per_second": 2.719,
|
| 269 |
+
"step": 468
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 14.0,
|
| 273 |
+
"grad_norm": 4.721966743469238,
|
| 274 |
+
"learning_rate": 2.7961165048543692e-05,
|
| 275 |
+
"loss": 0.6948,
|
| 276 |
+
"step": 504
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 14.0,
|
| 280 |
+
"eval_accuracy": 0.012268926056338027,
|
| 281 |
+
"eval_bleu": 0.36203576750790184,
|
| 282 |
+
"eval_f1": 0.011535961695115268,
|
| 283 |
+
"eval_loss": 1.4401381015777588,
|
| 284 |
+
"eval_precision": 0.010887377543860504,
|
| 285 |
+
"eval_recall": 0.012268926056338027,
|
| 286 |
+
"eval_runtime": 6.8054,
|
| 287 |
+
"eval_samples_per_second": 20.866,
|
| 288 |
+
"eval_steps_per_second": 2.645,
|
| 289 |
+
"step": 504
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 15.0,
|
| 293 |
+
"grad_norm": 3.970003128051758,
|
| 294 |
+
"learning_rate": 2.6213592233009708e-05,
|
| 295 |
+
"loss": 0.646,
|
| 296 |
+
"step": 540
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 15.0,
|
| 300 |
+
"eval_accuracy": 0.012048855633802816,
|
| 301 |
+
"eval_bleu": 0.37067819665088503,
|
| 302 |
+
"eval_f1": 0.011355838282605724,
|
| 303 |
+
"eval_loss": 1.4626511335372925,
|
| 304 |
+
"eval_precision": 0.010738384191565671,
|
| 305 |
+
"eval_recall": 0.012048855633802815,
|
| 306 |
+
"eval_runtime": 6.6898,
|
| 307 |
+
"eval_samples_per_second": 21.226,
|
| 308 |
+
"eval_steps_per_second": 2.691,
|
| 309 |
+
"step": 540
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 16.0,
|
| 313 |
+
"grad_norm": 3.967465877532959,
|
| 314 |
+
"learning_rate": 2.446601941747573e-05,
|
| 315 |
+
"loss": 0.6137,
|
| 316 |
+
"step": 576
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 16.0,
|
| 320 |
+
"eval_accuracy": 0.012048855633802816,
|
| 321 |
+
"eval_bleu": 0.3721186663899375,
|
| 322 |
+
"eval_f1": 0.01150499351512691,
|
| 323 |
+
"eval_loss": 1.460695505142212,
|
| 324 |
+
"eval_precision": 0.01100817275358665,
|
| 325 |
+
"eval_recall": 0.012048855633802815,
|
| 326 |
+
"eval_runtime": 6.1473,
|
| 327 |
+
"eval_samples_per_second": 23.1,
|
| 328 |
+
"eval_steps_per_second": 2.928,
|
| 329 |
+
"step": 576
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 17.0,
|
| 333 |
+
"grad_norm": 3.9431395530700684,
|
| 334 |
+
"learning_rate": 2.2718446601941746e-05,
|
| 335 |
+
"loss": 0.5833,
|
| 336 |
+
"step": 612
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 17.0,
|
| 340 |
+
"eval_accuracy": 0.012048855633802816,
|
| 341 |
+
"eval_bleu": 0.3782352067209992,
|
| 342 |
+
"eval_f1": 0.011355838282605724,
|
| 343 |
+
"eval_loss": 1.4740684032440186,
|
| 344 |
+
"eval_precision": 0.010738384191565671,
|
| 345 |
+
"eval_recall": 0.012048855633802815,
|
| 346 |
+
"eval_runtime": 6.2111,
|
| 347 |
+
"eval_samples_per_second": 22.862,
|
| 348 |
+
"eval_steps_per_second": 2.898,
|
| 349 |
+
"step": 612
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 18.0,
|
| 353 |
+
"grad_norm": 4.299834251403809,
|
| 354 |
+
"learning_rate": 2.097087378640777e-05,
|
| 355 |
+
"loss": 0.5523,
|
| 356 |
+
"step": 648
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 18.0,
|
| 360 |
+
"eval_accuracy": 0.012048855633802816,
|
| 361 |
+
"eval_bleu": 0.38158208167842117,
|
| 362 |
+
"eval_f1": 0.011454837538514543,
|
| 363 |
+
"eval_loss": 1.4804751873016357,
|
| 364 |
+
"eval_precision": 0.010916734980993936,
|
| 365 |
+
"eval_recall": 0.012048855633802815,
|
| 366 |
+
"eval_runtime": 6.2563,
|
| 367 |
+
"eval_samples_per_second": 22.697,
|
| 368 |
+
"eval_steps_per_second": 2.877,
|
| 369 |
+
"step": 648
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 19.0,
|
| 373 |
+
"grad_norm": 3.584228038787842,
|
| 374 |
+
"learning_rate": 1.9223300970873785e-05,
|
| 375 |
+
"loss": 0.5282,
|
| 376 |
+
"step": 684
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 19.0,
|
| 380 |
+
"eval_accuracy": 0.012268926056338027,
|
| 381 |
+
"eval_bleu": 0.38941442914279584,
|
| 382 |
+
"eval_f1": 0.011665531630013295,
|
| 383 |
+
"eval_loss": 1.4897931814193726,
|
| 384 |
+
"eval_precision": 0.011119728166708294,
|
| 385 |
+
"eval_recall": 0.012268926056338027,
|
| 386 |
+
"eval_runtime": 6.1705,
|
| 387 |
+
"eval_samples_per_second": 23.013,
|
| 388 |
+
"eval_steps_per_second": 2.917,
|
| 389 |
+
"step": 684
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 20.0,
|
| 393 |
+
"grad_norm": 3.575045108795166,
|
| 394 |
+
"learning_rate": 1.7475728155339808e-05,
|
| 395 |
+
"loss": 0.5047,
|
| 396 |
+
"step": 720
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 20.0,
|
| 400 |
+
"eval_accuracy": 0.01210387323943662,
|
| 401 |
+
"eval_bleu": 0.3904044704756756,
|
| 402 |
+
"eval_f1": 0.011583122303403293,
|
| 403 |
+
"eval_loss": 1.4997267723083496,
|
| 404 |
+
"eval_precision": 0.011105397197031464,
|
| 405 |
+
"eval_recall": 0.01210387323943662,
|
| 406 |
+
"eval_runtime": 6.3359,
|
| 407 |
+
"eval_samples_per_second": 22.412,
|
| 408 |
+
"eval_steps_per_second": 2.841,
|
| 409 |
+
"step": 720
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 21.0,
|
| 413 |
+
"grad_norm": 3.5939736366271973,
|
| 414 |
+
"learning_rate": 1.5728155339805823e-05,
|
| 415 |
+
"loss": 0.4854,
|
| 416 |
+
"step": 756
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 21.0,
|
| 420 |
+
"eval_accuracy": 0.012048855633802816,
|
| 421 |
+
"eval_bleu": 0.38824458290957736,
|
| 422 |
+
"eval_f1": 0.011442367439933718,
|
| 423 |
+
"eval_loss": 1.5054779052734375,
|
| 424 |
+
"eval_precision": 0.010894114653359857,
|
| 425 |
+
"eval_recall": 0.012048855633802815,
|
| 426 |
+
"eval_runtime": 6.2963,
|
| 427 |
+
"eval_samples_per_second": 22.553,
|
| 428 |
+
"eval_steps_per_second": 2.859,
|
| 429 |
+
"step": 756
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 22.0,
|
| 433 |
+
"grad_norm": 3.807431697845459,
|
| 434 |
+
"learning_rate": 1.3980582524271846e-05,
|
| 435 |
+
"loss": 0.4697,
|
| 436 |
+
"step": 792
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 22.0,
|
| 440 |
+
"eval_accuracy": 0.012048855633802816,
|
| 441 |
+
"eval_bleu": 0.3905756115063895,
|
| 442 |
+
"eval_f1": 0.011442367439933718,
|
| 443 |
+
"eval_loss": 1.5122706890106201,
|
| 444 |
+
"eval_precision": 0.010894114653359857,
|
| 445 |
+
"eval_recall": 0.012048855633802815,
|
| 446 |
+
"eval_runtime": 7.012,
|
| 447 |
+
"eval_samples_per_second": 20.251,
|
| 448 |
+
"eval_steps_per_second": 2.567,
|
| 449 |
+
"step": 792
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 23.0,
|
| 453 |
+
"grad_norm": 3.8207340240478516,
|
| 454 |
+
"learning_rate": 1.2233009708737865e-05,
|
| 455 |
+
"loss": 0.4547,
|
| 456 |
+
"step": 828
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 23.0,
|
| 460 |
+
"eval_accuracy": 0.012048855633802816,
|
| 461 |
+
"eval_bleu": 0.39316674027140547,
|
| 462 |
+
"eval_f1": 0.011517601862123769,
|
| 463 |
+
"eval_loss": 1.5183604955673218,
|
| 464 |
+
"eval_precision": 0.011031274351852924,
|
| 465 |
+
"eval_recall": 0.012048855633802815,
|
| 466 |
+
"eval_runtime": 6.8261,
|
| 467 |
+
"eval_samples_per_second": 20.803,
|
| 468 |
+
"eval_steps_per_second": 2.637,
|
| 469 |
+
"step": 828
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 24.0,
|
| 473 |
+
"grad_norm": 3.831852912902832,
|
| 474 |
+
"learning_rate": 1.0485436893203885e-05,
|
| 475 |
+
"loss": 0.4413,
|
| 476 |
+
"step": 864
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 24.0,
|
| 480 |
+
"eval_accuracy": 0.012048855633802816,
|
| 481 |
+
"eval_bleu": 0.3956605229111985,
|
| 482 |
+
"eval_f1": 0.011392759914288347,
|
| 483 |
+
"eval_loss": 1.5295231342315674,
|
| 484 |
+
"eval_precision": 0.010804571945629947,
|
| 485 |
+
"eval_recall": 0.012048855633802815,
|
| 486 |
+
"eval_runtime": 6.289,
|
| 487 |
+
"eval_samples_per_second": 22.579,
|
| 488 |
+
"eval_steps_per_second": 2.862,
|
| 489 |
+
"step": 864
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 25.0,
|
| 493 |
+
"grad_norm": 3.056539297103882,
|
| 494 |
+
"learning_rate": 8.737864077669904e-06,
|
| 495 |
+
"loss": 0.4325,
|
| 496 |
+
"step": 900
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 25.0,
|
| 500 |
+
"eval_accuracy": 0.012048855633802816,
|
| 501 |
+
"eval_bleu": 0.39496386454550636,
|
| 502 |
+
"eval_f1": 0.0114798602280593,
|
| 503 |
+
"eval_loss": 1.535691738128662,
|
| 504 |
+
"eval_precision": 0.010962261366716413,
|
| 505 |
+
"eval_recall": 0.012048855633802815,
|
| 506 |
+
"eval_runtime": 6.1059,
|
| 507 |
+
"eval_samples_per_second": 23.256,
|
| 508 |
+
"eval_steps_per_second": 2.948,
|
| 509 |
+
"step": 900
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 26.0,
|
| 513 |
+
"grad_norm": 3.1146154403686523,
|
| 514 |
+
"learning_rate": 6.990291262135923e-06,
|
| 515 |
+
"loss": 0.4188,
|
| 516 |
+
"step": 936
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 26.0,
|
| 520 |
+
"eval_accuracy": 0.012048855633802816,
|
| 521 |
+
"eval_bleu": 0.3960440421138887,
|
| 522 |
+
"eval_f1": 0.011517601862123769,
|
| 523 |
+
"eval_loss": 1.5396318435668945,
|
| 524 |
+
"eval_precision": 0.011031274351852924,
|
| 525 |
+
"eval_recall": 0.012048855633802815,
|
| 526 |
+
"eval_runtime": 7.2756,
|
| 527 |
+
"eval_samples_per_second": 19.517,
|
| 528 |
+
"eval_steps_per_second": 2.474,
|
| 529 |
+
"step": 936
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 27.0,
|
| 533 |
+
"grad_norm": 3.4233100414276123,
|
| 534 |
+
"learning_rate": 5.242718446601942e-06,
|
| 535 |
+
"loss": 0.4131,
|
| 536 |
+
"step": 972
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 27.0,
|
| 540 |
+
"eval_accuracy": 0.012048855633802816,
|
| 541 |
+
"eval_bleu": 0.4001388307186371,
|
| 542 |
+
"eval_f1": 0.011492413001125629,
|
| 543 |
+
"eval_loss": 1.5463387966156006,
|
| 544 |
+
"eval_precision": 0.010985168630418547,
|
| 545 |
+
"eval_recall": 0.012048855633802815,
|
| 546 |
+
"eval_runtime": 7.2564,
|
| 547 |
+
"eval_samples_per_second": 19.569,
|
| 548 |
+
"eval_steps_per_second": 2.481,
|
| 549 |
+
"step": 972
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 28.0,
|
| 553 |
+
"grad_norm": 2.70424485206604,
|
| 554 |
+
"learning_rate": 3.4951456310679615e-06,
|
| 555 |
+
"loss": 0.4089,
|
| 556 |
+
"step": 1008
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 28.0,
|
| 560 |
+
"eval_accuracy": 0.012048855633802816,
|
| 561 |
+
"eval_bleu": 0.39854032138633055,
|
| 562 |
+
"eval_f1": 0.011492413001125629,
|
| 563 |
+
"eval_loss": 1.544076681137085,
|
| 564 |
+
"eval_precision": 0.010985168630418547,
|
| 565 |
+
"eval_recall": 0.012048855633802815,
|
| 566 |
+
"eval_runtime": 7.0435,
|
| 567 |
+
"eval_samples_per_second": 20.16,
|
| 568 |
+
"eval_steps_per_second": 2.556,
|
| 569 |
+
"step": 1008
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 29.0,
|
| 573 |
+
"grad_norm": 3.052654266357422,
|
| 574 |
+
"learning_rate": 1.7475728155339808e-06,
|
| 575 |
+
"loss": 0.4026,
|
| 576 |
+
"step": 1044
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 29.0,
|
| 580 |
+
"eval_accuracy": 0.012048855633802816,
|
| 581 |
+
"eval_bleu": 0.3987203294842987,
|
| 582 |
+
"eval_f1": 0.01150499351512691,
|
| 583 |
+
"eval_loss": 1.5447367429733276,
|
| 584 |
+
"eval_precision": 0.01100817275358665,
|
| 585 |
+
"eval_recall": 0.012048855633802815,
|
| 586 |
+
"eval_runtime": 6.3248,
|
| 587 |
+
"eval_samples_per_second": 22.451,
|
| 588 |
+
"eval_steps_per_second": 2.846,
|
| 589 |
+
"step": 1044
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 30.0,
|
| 593 |
+
"grad_norm": 3.11586856842041,
|
| 594 |
+
"learning_rate": 0.0,
|
| 595 |
+
"loss": 0.3999,
|
| 596 |
+
"step": 1080
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 30.0,
|
| 600 |
+
"eval_accuracy": 0.012048855633802816,
|
| 601 |
+
"eval_bleu": 0.398637528263251,
|
| 602 |
+
"eval_f1": 0.011517601862123769,
|
| 603 |
+
"eval_loss": 1.5456310510635376,
|
| 604 |
+
"eval_precision": 0.011031274351852924,
|
| 605 |
+
"eval_recall": 0.012048855633802815,
|
| 606 |
+
"eval_runtime": 6.2921,
|
| 607 |
+
"eval_samples_per_second": 22.568,
|
| 608 |
+
"eval_steps_per_second": 2.861,
|
| 609 |
+
"step": 1080
|
| 610 |
+
}
|
| 611 |
+
],
|
| 612 |
+
"logging_steps": 500,
|
| 613 |
+
"max_steps": 1080,
|
| 614 |
+
"num_input_tokens_seen": 0,
|
| 615 |
+
"num_train_epochs": 30,
|
| 616 |
+
"save_steps": 500,
|
| 617 |
+
"stateful_callbacks": {
|
| 618 |
+
"TrainerControl": {
|
| 619 |
+
"args": {
|
| 620 |
+
"should_epoch_stop": false,
|
| 621 |
+
"should_evaluate": false,
|
| 622 |
+
"should_log": false,
|
| 623 |
+
"should_save": true,
|
| 624 |
+
"should_training_stop": true
|
| 625 |
+
},
|
| 626 |
+
"attributes": {}
|
| 627 |
+
}
|
| 628 |
+
},
|
| 629 |
+
"total_flos": 1113104056320000.0,
|
| 630 |
+
"train_batch_size": 16,
|
| 631 |
+
"trial_name": null,
|
| 632 |
+
"trial_params": null
|
| 633 |
+
}
|
checkpoint-1080/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f557e25922091b17e468d8ac6bc55cff0ff7201c8dce20c9bd3ed8370a6bba5
|
| 3 |
+
size 5048
|
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 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": 1024,
|
| 20 |
+
"reorder_and_upcast_attn": false,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.41.2",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50257
|
| 39 |
+
}
|
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": "4.41.2"
|
| 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:a8d22586f32398abba71287fc9fbd27f68a106fb4da5a21da85e439f4ea68d69
|
| 3 |
+
size 497774208
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"unk_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
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": true,
|
| 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": 1024,
|
| 19 |
+
"pad_token": null,
|
| 20 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 21 |
+
"unk_token": "<|endoftext|>"
|
| 22 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|