Training in progress, epoch 17, checkpoint
Browse files- checkpoint-2108/config.json +39 -0
- checkpoint-2108/generation_config.json +6 -0
- checkpoint-2108/merges.txt +0 -0
- checkpoint-2108/model.safetensors +3 -0
- checkpoint-2108/optimizer.pt +3 -0
- checkpoint-2108/rng_state.pth +3 -0
- checkpoint-2108/scheduler.pt +3 -0
- checkpoint-2108/special_tokens_map.json +6 -0
- checkpoint-2108/tokenizer.json +0 -0
- checkpoint-2108/tokenizer_config.json +21 -0
- checkpoint-2108/trainer_state.json +152 -0
- checkpoint-2108/training_args.bin +3 -0
- checkpoint-2108/vocab.json +0 -0
checkpoint-2108/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai-community/gpt2-large",
|
| 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": 1280,
|
| 16 |
+
"n_head": 20,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 36,
|
| 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": "4.47.1",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50257
|
| 39 |
+
}
|
checkpoint-2108/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": "4.47.1"
|
| 6 |
+
}
|
checkpoint-2108/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2108/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d782e8571381b5c8615dc5344489794273fb7a3e7ab8879e504ef272922f59d
|
| 3 |
+
size 3096165928
|
checkpoint-2108/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3865108b4e2da64e372c94e50001b3913fe0bcbe420abaa4352872f1d6baeee7
|
| 3 |
+
size 6192613990
|
checkpoint-2108/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6aeae495030bdd143b6d6d08905b7d4dd65c513cbf9aac0ae923ee7fd2ce9989
|
| 3 |
+
size 14244
|
checkpoint-2108/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba7be8490bca2eb4734e5fcc2793a33d1223866c9936bb12a438c576884103d7
|
| 3 |
+
size 1064
|
checkpoint-2108/special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
| 6 |
+
}
|
checkpoint-2108/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2108/tokenizer_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
}
|
| 12 |
+
},
|
| 13 |
+
"bos_token": "<|endoftext|>",
|
| 14 |
+
"clean_up_tokenization_spaces": false,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"extra_special_tokens": {},
|
| 17 |
+
"model_max_length": 1024,
|
| 18 |
+
"pad_token": "<|endoftext|>",
|
| 19 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 20 |
+
"unk_token": "<|endoftext|>"
|
| 21 |
+
}
|
checkpoint-2108/trainer_state.json
ADDED
|
@@ -0,0 +1,152 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 17.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2108,
|
| 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": 3.1197707653045654,
|
| 14 |
+
"learning_rate": 4.9692208514878444e-05,
|
| 15 |
+
"loss": 1.1128,
|
| 16 |
+
"step": 124
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 2.0,
|
| 20 |
+
"grad_norm": 1.8621318340301514,
|
| 21 |
+
"learning_rate": 4.877641290737884e-05,
|
| 22 |
+
"loss": 0.6276,
|
| 23 |
+
"step": 248
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 3.0,
|
| 27 |
+
"grad_norm": 1.429319143295288,
|
| 28 |
+
"learning_rate": 4.72751631047092e-05,
|
| 29 |
+
"loss": 0.4328,
|
| 30 |
+
"step": 372
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 4.0,
|
| 34 |
+
"grad_norm": 1.8360837697982788,
|
| 35 |
+
"learning_rate": 4.522542485937369e-05,
|
| 36 |
+
"loss": 0.3393,
|
| 37 |
+
"step": 496
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 5.0,
|
| 41 |
+
"grad_norm": 1.0911304950714111,
|
| 42 |
+
"learning_rate": 4.267766952966369e-05,
|
| 43 |
+
"loss": 0.2789,
|
| 44 |
+
"step": 620
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 6.0,
|
| 48 |
+
"grad_norm": 1.395412564277649,
|
| 49 |
+
"learning_rate": 3.969463130731183e-05,
|
| 50 |
+
"loss": 0.2392,
|
| 51 |
+
"step": 744
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 7.0,
|
| 55 |
+
"grad_norm": 0.8320960402488708,
|
| 56 |
+
"learning_rate": 3.634976249348867e-05,
|
| 57 |
+
"loss": 0.212,
|
| 58 |
+
"step": 868
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 8.0,
|
| 62 |
+
"grad_norm": 0.8032793402671814,
|
| 63 |
+
"learning_rate": 3.272542485937369e-05,
|
| 64 |
+
"loss": 0.1892,
|
| 65 |
+
"step": 992
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 9.0,
|
| 69 |
+
"grad_norm": 0.8925142288208008,
|
| 70 |
+
"learning_rate": 2.8910861626005776e-05,
|
| 71 |
+
"loss": 0.1727,
|
| 72 |
+
"step": 1116
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 10.0,
|
| 76 |
+
"grad_norm": 0.5616365671157837,
|
| 77 |
+
"learning_rate": 2.5e-05,
|
| 78 |
+
"loss": 0.1597,
|
| 79 |
+
"step": 1240
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 11.0,
|
| 83 |
+
"grad_norm": 0.6422319412231445,
|
| 84 |
+
"learning_rate": 2.1089138373994223e-05,
|
| 85 |
+
"loss": 0.1471,
|
| 86 |
+
"step": 1364
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 12.0,
|
| 90 |
+
"grad_norm": 0.9061075448989868,
|
| 91 |
+
"learning_rate": 1.7274575140626318e-05,
|
| 92 |
+
"loss": 0.1385,
|
| 93 |
+
"step": 1488
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 13.0,
|
| 97 |
+
"grad_norm": 0.6452886462211609,
|
| 98 |
+
"learning_rate": 1.3650237506511331e-05,
|
| 99 |
+
"loss": 0.1311,
|
| 100 |
+
"step": 1612
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 14.0,
|
| 104 |
+
"grad_norm": 0.6343705058097839,
|
| 105 |
+
"learning_rate": 1.0305368692688174e-05,
|
| 106 |
+
"loss": 0.1248,
|
| 107 |
+
"step": 1736
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 15.0,
|
| 111 |
+
"grad_norm": 0.5055845975875854,
|
| 112 |
+
"learning_rate": 7.3223304703363135e-06,
|
| 113 |
+
"loss": 0.1197,
|
| 114 |
+
"step": 1860
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 16.0,
|
| 118 |
+
"grad_norm": 0.5078000426292419,
|
| 119 |
+
"learning_rate": 4.7745751406263165e-06,
|
| 120 |
+
"loss": 0.1161,
|
| 121 |
+
"step": 1984
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 17.0,
|
| 125 |
+
"grad_norm": 0.48454469442367554,
|
| 126 |
+
"learning_rate": 2.7248368952908053e-06,
|
| 127 |
+
"loss": 0.1133,
|
| 128 |
+
"step": 2108
|
| 129 |
+
}
|
| 130 |
+
],
|
| 131 |
+
"logging_steps": 500,
|
| 132 |
+
"max_steps": 2480,
|
| 133 |
+
"num_input_tokens_seen": 0,
|
| 134 |
+
"num_train_epochs": 20,
|
| 135 |
+
"save_steps": 500,
|
| 136 |
+
"stateful_callbacks": {
|
| 137 |
+
"TrainerControl": {
|
| 138 |
+
"args": {
|
| 139 |
+
"should_epoch_stop": false,
|
| 140 |
+
"should_evaluate": false,
|
| 141 |
+
"should_log": false,
|
| 142 |
+
"should_save": true,
|
| 143 |
+
"should_training_stop": false
|
| 144 |
+
},
|
| 145 |
+
"attributes": {}
|
| 146 |
+
}
|
| 147 |
+
},
|
| 148 |
+
"total_flos": 1.62565353474816e+16,
|
| 149 |
+
"train_batch_size": 8,
|
| 150 |
+
"trial_name": null,
|
| 151 |
+
"trial_params": null
|
| 152 |
+
}
|
checkpoint-2108/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d641cc58aedf2c79ed6d2fe010d627feec4f355a064b510dc952c176c589fb1
|
| 3 |
+
size 5432
|
checkpoint-2108/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|