Upload fine-tuned GPT-2 dialogue model v2
Browse files- checkpoint-2548/config.json +38 -0
- checkpoint-2548/generation_config.json +6 -0
- checkpoint-2548/merges.txt +0 -0
- checkpoint-2548/model.safetensors +3 -0
- checkpoint-2548/optimizer.pt +3 -0
- checkpoint-2548/rng_state.pth +3 -0
- checkpoint-2548/scaler.pt +3 -0
- checkpoint-2548/scheduler.pt +3 -0
- checkpoint-2548/special_tokens_map.json +24 -0
- checkpoint-2548/tokenizer_config.json +23 -0
- checkpoint-2548/trainer_state.json +265 -0
- checkpoint-2548/training_args.bin +3 -0
- checkpoint-2548/vocab.json +0 -0
- checkpoint-2730/config.json +38 -0
- checkpoint-2730/generation_config.json +6 -0
- checkpoint-2730/merges.txt +0 -0
- checkpoint-2730/model.safetensors +3 -0
- checkpoint-2730/optimizer.pt +3 -0
- checkpoint-2730/rng_state.pth +3 -0
- checkpoint-2730/scaler.pt +3 -0
- checkpoint-2730/scheduler.pt +3 -0
- checkpoint-2730/special_tokens_map.json +24 -0
- checkpoint-2730/tokenizer_config.json +23 -0
- checkpoint-2730/trainer_state.json +280 -0
- checkpoint-2730/training_args.bin +3 -0
- checkpoint-2730/vocab.json +0 -0
- config.json +38 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer_config.json +23 -0
- vocab.json +0 -0
checkpoint-2548/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"dtype": "float32",
|
| 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 |
+
"transformers_version": "4.57.3",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50257
|
| 38 |
+
}
|
checkpoint-2548/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": "4.57.3"
|
| 6 |
+
}
|
checkpoint-2548/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2548/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6010c3e489ee87366458c79d44d85b7c8291fa7ab7dc3a7c523bfd5cbfa3cff
|
| 3 |
+
size 497774208
|
checkpoint-2548/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c12bd5de9aec0d1034fdc7524f14f8d4e16987d837b754ae94b2463269e0342d
|
| 3 |
+
size 995642763
|
checkpoint-2548/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30ac1131b50f7f9816b465f789b0e3d305dc942d7c01a377761dcb0113513b23
|
| 3 |
+
size 14645
|
checkpoint-2548/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a047abd089beec2b2259a7432932b821cc10a3dbec32a3fe72ab716224d327c
|
| 3 |
+
size 1383
|
checkpoint-2548/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b2b89fbc63e042c1595d51cc922e188a59fbb6b796370e3413bae020033edc9
|
| 3 |
+
size 1465
|
checkpoint-2548/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-2548/tokenizer_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 16 |
+
"eos_token": "<|endoftext|>",
|
| 17 |
+
"errors": "replace",
|
| 18 |
+
"extra_special_tokens": {},
|
| 19 |
+
"model_max_length": 1024,
|
| 20 |
+
"pad_token": "<|endoftext|>",
|
| 21 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 22 |
+
"unk_token": "<|endoftext|>"
|
| 23 |
+
}
|
checkpoint-2548/trainer_state.json
ADDED
|
@@ -0,0 +1,265 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2548,
|
| 3 |
+
"best_metric": 0.47001567482948303,
|
| 4 |
+
"best_model_checkpoint": "/content/gpt2-finetuned-dialogue-v2/checkpoint-2548",
|
| 5 |
+
"epoch": 14.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2548,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.797799174690509,
|
| 14 |
+
"grad_norm": 6.382191181182861,
|
| 15 |
+
"learning_rate": 4.329268292682927e-05,
|
| 16 |
+
"loss": 5.6544,
|
| 17 |
+
"step": 145
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.0,
|
| 21 |
+
"eval_loss": 2.7988412380218506,
|
| 22 |
+
"eval_runtime": 6.9158,
|
| 23 |
+
"eval_samples_per_second": 46.705,
|
| 24 |
+
"eval_steps_per_second": 11.712,
|
| 25 |
+
"step": 182
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.5942228335625859,
|
| 29 |
+
"grad_norm": 5.028477191925049,
|
| 30 |
+
"learning_rate": 4.760327357755262e-05,
|
| 31 |
+
"loss": 2.9373,
|
| 32 |
+
"step": 290
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_loss": 2.292213201522827,
|
| 37 |
+
"eval_runtime": 6.9846,
|
| 38 |
+
"eval_samples_per_second": 46.245,
|
| 39 |
+
"eval_steps_per_second": 11.597,
|
| 40 |
+
"step": 364
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 2.390646492434663,
|
| 44 |
+
"grad_norm": 5.537014484405518,
|
| 45 |
+
"learning_rate": 4.477786438035854e-05,
|
| 46 |
+
"loss": 2.4918,
|
| 47 |
+
"step": 435
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"eval_loss": 1.920114278793335,
|
| 52 |
+
"eval_runtime": 6.9658,
|
| 53 |
+
"eval_samples_per_second": 46.369,
|
| 54 |
+
"eval_steps_per_second": 11.628,
|
| 55 |
+
"step": 546
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 3.18707015130674,
|
| 59 |
+
"grad_norm": 4.482412338256836,
|
| 60 |
+
"learning_rate": 4.195245518316446e-05,
|
| 61 |
+
"loss": 2.1431,
|
| 62 |
+
"step": 580
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 3.984869325997249,
|
| 66 |
+
"grad_norm": 3.806051731109619,
|
| 67 |
+
"learning_rate": 3.912704598597038e-05,
|
| 68 |
+
"loss": 1.8536,
|
| 69 |
+
"step": 725
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.0,
|
| 73 |
+
"eval_loss": 1.5900342464447021,
|
| 74 |
+
"eval_runtime": 6.9658,
|
| 75 |
+
"eval_samples_per_second": 46.369,
|
| 76 |
+
"eval_steps_per_second": 11.628,
|
| 77 |
+
"step": 728
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 4.781292984869326,
|
| 81 |
+
"grad_norm": 4.049495220184326,
|
| 82 |
+
"learning_rate": 3.630163678877631e-05,
|
| 83 |
+
"loss": 1.5906,
|
| 84 |
+
"step": 870
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 5.0,
|
| 88 |
+
"eval_loss": 1.3074204921722412,
|
| 89 |
+
"eval_runtime": 6.9705,
|
| 90 |
+
"eval_samples_per_second": 46.338,
|
| 91 |
+
"eval_steps_per_second": 11.62,
|
| 92 |
+
"step": 910
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.577716643741403,
|
| 96 |
+
"grad_norm": 4.306301593780518,
|
| 97 |
+
"learning_rate": 3.3476227591582234e-05,
|
| 98 |
+
"loss": 1.3729,
|
| 99 |
+
"step": 1015
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 6.0,
|
| 103 |
+
"eval_loss": 1.0866929292678833,
|
| 104 |
+
"eval_runtime": 6.9232,
|
| 105 |
+
"eval_samples_per_second": 46.655,
|
| 106 |
+
"eval_steps_per_second": 11.7,
|
| 107 |
+
"step": 1092
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 6.37414030261348,
|
| 111 |
+
"grad_norm": 3.724321126937866,
|
| 112 |
+
"learning_rate": 3.065081839438815e-05,
|
| 113 |
+
"loss": 1.2009,
|
| 114 |
+
"step": 1160
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 7.0,
|
| 118 |
+
"eval_loss": 0.9100379347801208,
|
| 119 |
+
"eval_runtime": 6.9831,
|
| 120 |
+
"eval_samples_per_second": 46.255,
|
| 121 |
+
"eval_steps_per_second": 11.599,
|
| 122 |
+
"step": 1274
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 7.170563961485557,
|
| 126 |
+
"grad_norm": 3.3211708068847656,
|
| 127 |
+
"learning_rate": 2.782540919719408e-05,
|
| 128 |
+
"loss": 1.0504,
|
| 129 |
+
"step": 1305
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 7.968363136176066,
|
| 133 |
+
"grad_norm": 2.471958875656128,
|
| 134 |
+
"learning_rate": 2.5e-05,
|
| 135 |
+
"loss": 0.9314,
|
| 136 |
+
"step": 1450
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 8.0,
|
| 140 |
+
"eval_loss": 0.7771766781806946,
|
| 141 |
+
"eval_runtime": 7.0432,
|
| 142 |
+
"eval_samples_per_second": 45.86,
|
| 143 |
+
"eval_steps_per_second": 11.5,
|
| 144 |
+
"step": 1456
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 8.764786795048144,
|
| 148 |
+
"grad_norm": 2.442481517791748,
|
| 149 |
+
"learning_rate": 2.2174590802805924e-05,
|
| 150 |
+
"loss": 0.8322,
|
| 151 |
+
"step": 1595
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 9.0,
|
| 155 |
+
"eval_loss": 0.6769014000892639,
|
| 156 |
+
"eval_runtime": 6.9508,
|
| 157 |
+
"eval_samples_per_second": 46.47,
|
| 158 |
+
"eval_steps_per_second": 11.653,
|
| 159 |
+
"step": 1638
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 9.56121045392022,
|
| 163 |
+
"grad_norm": 2.086437940597534,
|
| 164 |
+
"learning_rate": 1.934918160561185e-05,
|
| 165 |
+
"loss": 0.7578,
|
| 166 |
+
"step": 1740
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 10.0,
|
| 170 |
+
"eval_loss": 0.601751446723938,
|
| 171 |
+
"eval_runtime": 6.9024,
|
| 172 |
+
"eval_samples_per_second": 46.795,
|
| 173 |
+
"eval_steps_per_second": 11.735,
|
| 174 |
+
"step": 1820
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 10.357634112792297,
|
| 178 |
+
"grad_norm": 2.158360481262207,
|
| 179 |
+
"learning_rate": 1.6523772408417772e-05,
|
| 180 |
+
"loss": 0.6874,
|
| 181 |
+
"step": 1885
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 11.0,
|
| 185 |
+
"eval_loss": 0.5506384372711182,
|
| 186 |
+
"eval_runtime": 7.0206,
|
| 187 |
+
"eval_samples_per_second": 46.008,
|
| 188 |
+
"eval_steps_per_second": 11.537,
|
| 189 |
+
"step": 2002
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 11.154057771664375,
|
| 193 |
+
"grad_norm": 2.359311819076538,
|
| 194 |
+
"learning_rate": 1.3698363211223694e-05,
|
| 195 |
+
"loss": 0.6506,
|
| 196 |
+
"step": 2030
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 11.951856946354884,
|
| 200 |
+
"grad_norm": 2.4090545177459717,
|
| 201 |
+
"learning_rate": 1.0872954014029618e-05,
|
| 202 |
+
"loss": 0.6091,
|
| 203 |
+
"step": 2175
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 12.0,
|
| 207 |
+
"eval_loss": 0.5107725858688354,
|
| 208 |
+
"eval_runtime": 6.9921,
|
| 209 |
+
"eval_samples_per_second": 46.195,
|
| 210 |
+
"eval_steps_per_second": 11.584,
|
| 211 |
+
"step": 2184
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 12.74828060522696,
|
| 215 |
+
"grad_norm": 2.641254425048828,
|
| 216 |
+
"learning_rate": 8.047544816835542e-06,
|
| 217 |
+
"loss": 0.581,
|
| 218 |
+
"step": 2320
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 13.0,
|
| 222 |
+
"eval_loss": 0.48598870635032654,
|
| 223 |
+
"eval_runtime": 7.0084,
|
| 224 |
+
"eval_samples_per_second": 46.087,
|
| 225 |
+
"eval_steps_per_second": 11.557,
|
| 226 |
+
"step": 2366
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 13.544704264099037,
|
| 230 |
+
"grad_norm": 2.234863042831421,
|
| 231 |
+
"learning_rate": 5.222135619641466e-06,
|
| 232 |
+
"loss": 0.5598,
|
| 233 |
+
"step": 2465
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 14.0,
|
| 237 |
+
"eval_loss": 0.47001567482948303,
|
| 238 |
+
"eval_runtime": 6.9078,
|
| 239 |
+
"eval_samples_per_second": 46.759,
|
| 240 |
+
"eval_steps_per_second": 11.726,
|
| 241 |
+
"step": 2548
|
| 242 |
+
}
|
| 243 |
+
],
|
| 244 |
+
"logging_steps": 145,
|
| 245 |
+
"max_steps": 2730,
|
| 246 |
+
"num_input_tokens_seen": 0,
|
| 247 |
+
"num_train_epochs": 15,
|
| 248 |
+
"save_steps": 500,
|
| 249 |
+
"stateful_callbacks": {
|
| 250 |
+
"TrainerControl": {
|
| 251 |
+
"args": {
|
| 252 |
+
"should_epoch_stop": false,
|
| 253 |
+
"should_evaluate": false,
|
| 254 |
+
"should_log": false,
|
| 255 |
+
"should_save": true,
|
| 256 |
+
"should_training_stop": false
|
| 257 |
+
},
|
| 258 |
+
"attributes": {}
|
| 259 |
+
}
|
| 260 |
+
},
|
| 261 |
+
"total_flos": 1.0630405029888e+16,
|
| 262 |
+
"train_batch_size": 4,
|
| 263 |
+
"trial_name": null,
|
| 264 |
+
"trial_params": null
|
| 265 |
+
}
|
checkpoint-2548/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7db1c3b396ab4647640791be8eb5e64ed0e1caa1b2e2d95e1461f28d187f1f6d
|
| 3 |
+
size 5841
|
checkpoint-2548/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2730/config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"dtype": "float32",
|
| 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 |
+
"transformers_version": "4.57.3",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50257
|
| 38 |
+
}
|
checkpoint-2730/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": "4.57.3"
|
| 6 |
+
}
|
checkpoint-2730/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2730/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4746335bd649570cce06cb14d3637b472ecd72c73fbada2481eb85a4a61b28ed
|
| 3 |
+
size 497774208
|
checkpoint-2730/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a39fcf238f79cc2934d0d85ab8c9a1e68f57b4cb70c4cc4183a7813d9c499bd
|
| 3 |
+
size 995642763
|
checkpoint-2730/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7104f369380c0b85fbaa81296ed76192ad576305fe06eaa696125d472db42b7a
|
| 3 |
+
size 14645
|
checkpoint-2730/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d2ac9124a3f9d71861ec987ee52c91d65f4aae60c8c559f2d0bdb8f6b576e57
|
| 3 |
+
size 1383
|
checkpoint-2730/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96fd98ecacf62de2e67018478f3ead54588efc958f4279fb68a061b5d6e7ed41
|
| 3 |
+
size 1465
|
checkpoint-2730/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-2730/tokenizer_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 16 |
+
"eos_token": "<|endoftext|>",
|
| 17 |
+
"errors": "replace",
|
| 18 |
+
"extra_special_tokens": {},
|
| 19 |
+
"model_max_length": 1024,
|
| 20 |
+
"pad_token": "<|endoftext|>",
|
| 21 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 22 |
+
"unk_token": "<|endoftext|>"
|
| 23 |
+
}
|
checkpoint-2730/trainer_state.json
ADDED
|
@@ -0,0 +1,280 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2730,
|
| 3 |
+
"best_metric": 0.4640800952911377,
|
| 4 |
+
"best_model_checkpoint": "/content/gpt2-finetuned-dialogue-v2/checkpoint-2730",
|
| 5 |
+
"epoch": 15.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2730,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.797799174690509,
|
| 14 |
+
"grad_norm": 6.382191181182861,
|
| 15 |
+
"learning_rate": 4.329268292682927e-05,
|
| 16 |
+
"loss": 5.6544,
|
| 17 |
+
"step": 145
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.0,
|
| 21 |
+
"eval_loss": 2.7988412380218506,
|
| 22 |
+
"eval_runtime": 6.9158,
|
| 23 |
+
"eval_samples_per_second": 46.705,
|
| 24 |
+
"eval_steps_per_second": 11.712,
|
| 25 |
+
"step": 182
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.5942228335625859,
|
| 29 |
+
"grad_norm": 5.028477191925049,
|
| 30 |
+
"learning_rate": 4.760327357755262e-05,
|
| 31 |
+
"loss": 2.9373,
|
| 32 |
+
"step": 290
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_loss": 2.292213201522827,
|
| 37 |
+
"eval_runtime": 6.9846,
|
| 38 |
+
"eval_samples_per_second": 46.245,
|
| 39 |
+
"eval_steps_per_second": 11.597,
|
| 40 |
+
"step": 364
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 2.390646492434663,
|
| 44 |
+
"grad_norm": 5.537014484405518,
|
| 45 |
+
"learning_rate": 4.477786438035854e-05,
|
| 46 |
+
"loss": 2.4918,
|
| 47 |
+
"step": 435
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"eval_loss": 1.920114278793335,
|
| 52 |
+
"eval_runtime": 6.9658,
|
| 53 |
+
"eval_samples_per_second": 46.369,
|
| 54 |
+
"eval_steps_per_second": 11.628,
|
| 55 |
+
"step": 546
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 3.18707015130674,
|
| 59 |
+
"grad_norm": 4.482412338256836,
|
| 60 |
+
"learning_rate": 4.195245518316446e-05,
|
| 61 |
+
"loss": 2.1431,
|
| 62 |
+
"step": 580
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 3.984869325997249,
|
| 66 |
+
"grad_norm": 3.806051731109619,
|
| 67 |
+
"learning_rate": 3.912704598597038e-05,
|
| 68 |
+
"loss": 1.8536,
|
| 69 |
+
"step": 725
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.0,
|
| 73 |
+
"eval_loss": 1.5900342464447021,
|
| 74 |
+
"eval_runtime": 6.9658,
|
| 75 |
+
"eval_samples_per_second": 46.369,
|
| 76 |
+
"eval_steps_per_second": 11.628,
|
| 77 |
+
"step": 728
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 4.781292984869326,
|
| 81 |
+
"grad_norm": 4.049495220184326,
|
| 82 |
+
"learning_rate": 3.630163678877631e-05,
|
| 83 |
+
"loss": 1.5906,
|
| 84 |
+
"step": 870
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 5.0,
|
| 88 |
+
"eval_loss": 1.3074204921722412,
|
| 89 |
+
"eval_runtime": 6.9705,
|
| 90 |
+
"eval_samples_per_second": 46.338,
|
| 91 |
+
"eval_steps_per_second": 11.62,
|
| 92 |
+
"step": 910
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.577716643741403,
|
| 96 |
+
"grad_norm": 4.306301593780518,
|
| 97 |
+
"learning_rate": 3.3476227591582234e-05,
|
| 98 |
+
"loss": 1.3729,
|
| 99 |
+
"step": 1015
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 6.0,
|
| 103 |
+
"eval_loss": 1.0866929292678833,
|
| 104 |
+
"eval_runtime": 6.9232,
|
| 105 |
+
"eval_samples_per_second": 46.655,
|
| 106 |
+
"eval_steps_per_second": 11.7,
|
| 107 |
+
"step": 1092
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 6.37414030261348,
|
| 111 |
+
"grad_norm": 3.724321126937866,
|
| 112 |
+
"learning_rate": 3.065081839438815e-05,
|
| 113 |
+
"loss": 1.2009,
|
| 114 |
+
"step": 1160
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 7.0,
|
| 118 |
+
"eval_loss": 0.9100379347801208,
|
| 119 |
+
"eval_runtime": 6.9831,
|
| 120 |
+
"eval_samples_per_second": 46.255,
|
| 121 |
+
"eval_steps_per_second": 11.599,
|
| 122 |
+
"step": 1274
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 7.170563961485557,
|
| 126 |
+
"grad_norm": 3.3211708068847656,
|
| 127 |
+
"learning_rate": 2.782540919719408e-05,
|
| 128 |
+
"loss": 1.0504,
|
| 129 |
+
"step": 1305
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 7.968363136176066,
|
| 133 |
+
"grad_norm": 2.471958875656128,
|
| 134 |
+
"learning_rate": 2.5e-05,
|
| 135 |
+
"loss": 0.9314,
|
| 136 |
+
"step": 1450
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 8.0,
|
| 140 |
+
"eval_loss": 0.7771766781806946,
|
| 141 |
+
"eval_runtime": 7.0432,
|
| 142 |
+
"eval_samples_per_second": 45.86,
|
| 143 |
+
"eval_steps_per_second": 11.5,
|
| 144 |
+
"step": 1456
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 8.764786795048144,
|
| 148 |
+
"grad_norm": 2.442481517791748,
|
| 149 |
+
"learning_rate": 2.2174590802805924e-05,
|
| 150 |
+
"loss": 0.8322,
|
| 151 |
+
"step": 1595
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 9.0,
|
| 155 |
+
"eval_loss": 0.6769014000892639,
|
| 156 |
+
"eval_runtime": 6.9508,
|
| 157 |
+
"eval_samples_per_second": 46.47,
|
| 158 |
+
"eval_steps_per_second": 11.653,
|
| 159 |
+
"step": 1638
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 9.56121045392022,
|
| 163 |
+
"grad_norm": 2.086437940597534,
|
| 164 |
+
"learning_rate": 1.934918160561185e-05,
|
| 165 |
+
"loss": 0.7578,
|
| 166 |
+
"step": 1740
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 10.0,
|
| 170 |
+
"eval_loss": 0.601751446723938,
|
| 171 |
+
"eval_runtime": 6.9024,
|
| 172 |
+
"eval_samples_per_second": 46.795,
|
| 173 |
+
"eval_steps_per_second": 11.735,
|
| 174 |
+
"step": 1820
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 10.357634112792297,
|
| 178 |
+
"grad_norm": 2.158360481262207,
|
| 179 |
+
"learning_rate": 1.6523772408417772e-05,
|
| 180 |
+
"loss": 0.6874,
|
| 181 |
+
"step": 1885
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 11.0,
|
| 185 |
+
"eval_loss": 0.5506384372711182,
|
| 186 |
+
"eval_runtime": 7.0206,
|
| 187 |
+
"eval_samples_per_second": 46.008,
|
| 188 |
+
"eval_steps_per_second": 11.537,
|
| 189 |
+
"step": 2002
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 11.154057771664375,
|
| 193 |
+
"grad_norm": 2.359311819076538,
|
| 194 |
+
"learning_rate": 1.3698363211223694e-05,
|
| 195 |
+
"loss": 0.6506,
|
| 196 |
+
"step": 2030
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 11.951856946354884,
|
| 200 |
+
"grad_norm": 2.4090545177459717,
|
| 201 |
+
"learning_rate": 1.0872954014029618e-05,
|
| 202 |
+
"loss": 0.6091,
|
| 203 |
+
"step": 2175
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 12.0,
|
| 207 |
+
"eval_loss": 0.5107725858688354,
|
| 208 |
+
"eval_runtime": 6.9921,
|
| 209 |
+
"eval_samples_per_second": 46.195,
|
| 210 |
+
"eval_steps_per_second": 11.584,
|
| 211 |
+
"step": 2184
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 12.74828060522696,
|
| 215 |
+
"grad_norm": 2.641254425048828,
|
| 216 |
+
"learning_rate": 8.047544816835542e-06,
|
| 217 |
+
"loss": 0.581,
|
| 218 |
+
"step": 2320
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 13.0,
|
| 222 |
+
"eval_loss": 0.48598870635032654,
|
| 223 |
+
"eval_runtime": 7.0084,
|
| 224 |
+
"eval_samples_per_second": 46.087,
|
| 225 |
+
"eval_steps_per_second": 11.557,
|
| 226 |
+
"step": 2366
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 13.544704264099037,
|
| 230 |
+
"grad_norm": 2.234863042831421,
|
| 231 |
+
"learning_rate": 5.222135619641466e-06,
|
| 232 |
+
"loss": 0.5598,
|
| 233 |
+
"step": 2465
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 14.0,
|
| 237 |
+
"eval_loss": 0.47001567482948303,
|
| 238 |
+
"eval_runtime": 6.9078,
|
| 239 |
+
"eval_samples_per_second": 46.759,
|
| 240 |
+
"eval_steps_per_second": 11.726,
|
| 241 |
+
"step": 2548
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 14.341127922971115,
|
| 245 |
+
"grad_norm": 2.0931003093719482,
|
| 246 |
+
"learning_rate": 2.396726422447389e-06,
|
| 247 |
+
"loss": 0.542,
|
| 248 |
+
"step": 2610
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 15.0,
|
| 252 |
+
"eval_loss": 0.4640800952911377,
|
| 253 |
+
"eval_runtime": 6.9334,
|
| 254 |
+
"eval_samples_per_second": 46.586,
|
| 255 |
+
"eval_steps_per_second": 11.683,
|
| 256 |
+
"step": 2730
|
| 257 |
+
}
|
| 258 |
+
],
|
| 259 |
+
"logging_steps": 145,
|
| 260 |
+
"max_steps": 2730,
|
| 261 |
+
"num_input_tokens_seen": 0,
|
| 262 |
+
"num_train_epochs": 15,
|
| 263 |
+
"save_steps": 500,
|
| 264 |
+
"stateful_callbacks": {
|
| 265 |
+
"TrainerControl": {
|
| 266 |
+
"args": {
|
| 267 |
+
"should_epoch_stop": false,
|
| 268 |
+
"should_evaluate": false,
|
| 269 |
+
"should_log": false,
|
| 270 |
+
"should_save": true,
|
| 271 |
+
"should_training_stop": true
|
| 272 |
+
},
|
| 273 |
+
"attributes": {}
|
| 274 |
+
}
|
| 275 |
+
},
|
| 276 |
+
"total_flos": 1.138971967488e+16,
|
| 277 |
+
"train_batch_size": 4,
|
| 278 |
+
"trial_name": null,
|
| 279 |
+
"trial_params": null
|
| 280 |
+
}
|
checkpoint-2730/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7db1c3b396ab4647640791be8eb5e64ed0e1caa1b2e2d95e1461f28d187f1f6d
|
| 3 |
+
size 5841
|
checkpoint-2730/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"dtype": "float32",
|
| 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 |
+
"transformers_version": "4.57.3",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50257
|
| 38 |
+
}
|
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": "4.57.3"
|
| 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 sha256:4746335bd649570cce06cb14d3637b472ecd72c73fbada2481eb85a4a61b28ed
|
| 3 |
+
size 497774208
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 16 |
+
"eos_token": "<|endoftext|>",
|
| 17 |
+
"errors": "replace",
|
| 18 |
+
"extra_special_tokens": {},
|
| 19 |
+
"model_max_length": 1024,
|
| 20 |
+
"pad_token": "<|endoftext|>",
|
| 21 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 22 |
+
"unk_token": "<|endoftext|>"
|
| 23 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|