Upload folder using huggingface_hub
Browse files- chat_template.jinja +7 -0
- checkpoint-268/chat_template.jinja +7 -0
- checkpoint-268/config.json +41 -0
- checkpoint-268/generation_config.json +9 -0
- checkpoint-268/model.safetensors +3 -0
- checkpoint-268/optimizer.pt +3 -0
- checkpoint-268/rng_state.pth +3 -0
- checkpoint-268/scheduler.pt +3 -0
- checkpoint-268/tokenizer.json +0 -0
- checkpoint-268/tokenizer_config.json +18 -0
- checkpoint-268/trainer_state.json +224 -0
- checkpoint-268/training_args.bin +3 -0
- checkpoint-536/chat_template.jinja +7 -0
- checkpoint-536/config.json +41 -0
- checkpoint-536/generation_config.json +9 -0
- checkpoint-536/model.safetensors +3 -0
- checkpoint-536/optimizer.pt +3 -0
- checkpoint-536/rng_state.pth +3 -0
- checkpoint-536/scheduler.pt +3 -0
- checkpoint-536/tokenizer.json +0 -0
- checkpoint-536/tokenizer_config.json +18 -0
- checkpoint-536/trainer_state.json +421 -0
- checkpoint-536/training_args.bin +3 -0
- config.json +41 -0
- generation_config.json +9 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +18 -0
- training_args.bin +3 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- for message in messages %}
|
| 2 |
+
{{- '<|im_start|>' + message['role'] + '\n' }}
|
| 3 |
+
{{- message['content'] + '<|im_end|>' }}
|
| 4 |
+
{%- endfor %}
|
| 5 |
+
{%- if add_generation_prompt %}
|
| 6 |
+
{{- '<|im_start|>assistant\n' }}
|
| 7 |
+
{%- endif %}
|
checkpoint-268/chat_template.jinja
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- for message in messages %}
|
| 2 |
+
{{- '<|im_start|>' + message['role'] + '\n' }}
|
| 3 |
+
{{- message['content'] + '<|im_end|>' }}
|
| 4 |
+
{%- endfor %}
|
| 5 |
+
{%- if add_generation_prompt %}
|
| 6 |
+
{{- '<|im_start|>assistant\n' }}
|
| 7 |
+
{%- endif %}
|
checkpoint-268/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 768,
|
| 17 |
+
"n_head": 12,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 12,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"pad_token_id": 50257,
|
| 22 |
+
"reorder_and_upcast_attn": false,
|
| 23 |
+
"resid_pdrop": 0.1,
|
| 24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
+
"scale_attn_weights": true,
|
| 26 |
+
"summary_activation": null,
|
| 27 |
+
"summary_first_dropout": 0.1,
|
| 28 |
+
"summary_proj_to_labels": true,
|
| 29 |
+
"summary_type": "cls_index",
|
| 30 |
+
"summary_use_proj": true,
|
| 31 |
+
"task_specific_params": {
|
| 32 |
+
"text-generation": {
|
| 33 |
+
"do_sample": true,
|
| 34 |
+
"max_length": 50
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"tie_word_embeddings": true,
|
| 38 |
+
"transformers_version": "5.12.1",
|
| 39 |
+
"use_cache": false,
|
| 40 |
+
"vocab_size": 50261
|
| 41 |
+
}
|
checkpoint-268/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
50256
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 50257,
|
| 8 |
+
"transformers_version": "5.12.1"
|
| 9 |
+
}
|
checkpoint-268/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be42d5371be1ead45df0caf4dc2955a942e6fc48da63a74d9601a4feb42b675e
|
| 3 |
+
size 497786496
|
checkpoint-268/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6f6ed481f41b5c7a8aaddcddaff8918f5eb3fdf430a2e887fab22c38c5d74ab
|
| 3 |
+
size 995669387
|
checkpoint-268/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ed6f68e7e5fa036200a60323d12cdaaea7b8e3c43f52615876ef55c86461d64
|
| 3 |
+
size 14645
|
checkpoint-268/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:685ce8e5d7c8551174e1932920f0c4262907d225b7c4f4bacc8f9fafa6f3d916
|
| 3 |
+
size 1465
|
checkpoint-268/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-268/tokenizer_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|endoftext|>",
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"extra_special_tokens": [
|
| 8 |
+
"<|im_start|>",
|
| 9 |
+
"<|im_end|>",
|
| 10 |
+
"<|im_sep|>"
|
| 11 |
+
],
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"local_files_only": false,
|
| 14 |
+
"model_max_length": 1024,
|
| 15 |
+
"pad_token": "<|pad|>",
|
| 16 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 17 |
+
"unk_token": "<|endoftext|>"
|
| 18 |
+
}
|
checkpoint-268/trainer_state.json
ADDED
|
@@ -0,0 +1,224 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 268,
|
| 3 |
+
"best_metric": 2.9178810119628906,
|
| 4 |
+
"best_model_checkpoint": "gpt2-finetuned/checkpoint-268",
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 268,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.037383177570093455,
|
| 14 |
+
"grad_norm": 4.323858737945557,
|
| 15 |
+
"learning_rate": 1.0588235294117648e-05,
|
| 16 |
+
"loss": 3.5710372924804688,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.07476635514018691,
|
| 21 |
+
"grad_norm": 3.9307808876037598,
|
| 22 |
+
"learning_rate": 1.9922928709055876e-05,
|
| 23 |
+
"loss": 3.3915550231933596,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.11214953271028037,
|
| 28 |
+
"grad_norm": 3.703219175338745,
|
| 29 |
+
"learning_rate": 1.9537572254335264e-05,
|
| 30 |
+
"loss": 3.30927734375,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.14953271028037382,
|
| 35 |
+
"grad_norm": 3.3923251628875732,
|
| 36 |
+
"learning_rate": 1.9152215799614644e-05,
|
| 37 |
+
"loss": 3.2569236755371094,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.18691588785046728,
|
| 42 |
+
"grad_norm": 3.6839487552642822,
|
| 43 |
+
"learning_rate": 1.8766859344894028e-05,
|
| 44 |
+
"loss": 3.2078022003173827,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.22429906542056074,
|
| 49 |
+
"grad_norm": 3.1598305702209473,
|
| 50 |
+
"learning_rate": 1.838150289017341e-05,
|
| 51 |
+
"loss": 3.1958980560302734,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.2616822429906542,
|
| 56 |
+
"grad_norm": 3.5608792304992676,
|
| 57 |
+
"learning_rate": 1.7996146435452795e-05,
|
| 58 |
+
"loss": 3.1352081298828125,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.29906542056074764,
|
| 63 |
+
"grad_norm": 3.694288492202759,
|
| 64 |
+
"learning_rate": 1.761078998073218e-05,
|
| 65 |
+
"loss": 3.1180818557739256,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.3364485981308411,
|
| 70 |
+
"grad_norm": 3.2345361709594727,
|
| 71 |
+
"learning_rate": 1.722543352601156e-05,
|
| 72 |
+
"loss": 3.121156692504883,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.37383177570093457,
|
| 77 |
+
"grad_norm": 2.8083014488220215,
|
| 78 |
+
"learning_rate": 1.6840077071290947e-05,
|
| 79 |
+
"loss": 3.091750907897949,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.411214953271028,
|
| 84 |
+
"grad_norm": 3.5092177391052246,
|
| 85 |
+
"learning_rate": 1.645472061657033e-05,
|
| 86 |
+
"loss": 3.085820198059082,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.4485981308411215,
|
| 91 |
+
"grad_norm": 3.606647491455078,
|
| 92 |
+
"learning_rate": 1.606936416184971e-05,
|
| 93 |
+
"loss": 3.103367233276367,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.48598130841121495,
|
| 98 |
+
"grad_norm": 2.9848923683166504,
|
| 99 |
+
"learning_rate": 1.5684007707129095e-05,
|
| 100 |
+
"loss": 3.1185840606689452,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.5233644859813084,
|
| 105 |
+
"grad_norm": 3.9700093269348145,
|
| 106 |
+
"learning_rate": 1.529865125240848e-05,
|
| 107 |
+
"loss": 3.111907386779785,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.5607476635514018,
|
| 112 |
+
"grad_norm": 4.307053565979004,
|
| 113 |
+
"learning_rate": 1.4913294797687862e-05,
|
| 114 |
+
"loss": 3.1015724182128905,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.5981308411214953,
|
| 119 |
+
"grad_norm": 4.230574607849121,
|
| 120 |
+
"learning_rate": 1.4527938342967245e-05,
|
| 121 |
+
"loss": 3.1573991775512695,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.6355140186915887,
|
| 126 |
+
"grad_norm": 3.484198808670044,
|
| 127 |
+
"learning_rate": 1.414258188824663e-05,
|
| 128 |
+
"loss": 3.09665470123291,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.6728971962616822,
|
| 133 |
+
"grad_norm": 3.7458720207214355,
|
| 134 |
+
"learning_rate": 1.3757225433526014e-05,
|
| 135 |
+
"loss": 3.0797067642211915,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.7102803738317757,
|
| 140 |
+
"grad_norm": 3.599705457687378,
|
| 141 |
+
"learning_rate": 1.3371868978805396e-05,
|
| 142 |
+
"loss": 3.02014045715332,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.7476635514018691,
|
| 147 |
+
"grad_norm": 3.341883659362793,
|
| 148 |
+
"learning_rate": 1.298651252408478e-05,
|
| 149 |
+
"loss": 3.0037511825561523,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.7850467289719626,
|
| 154 |
+
"grad_norm": 3.6026880741119385,
|
| 155 |
+
"learning_rate": 1.2601156069364162e-05,
|
| 156 |
+
"loss": 2.995482063293457,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.822429906542056,
|
| 161 |
+
"grad_norm": 3.875734329223633,
|
| 162 |
+
"learning_rate": 1.2215799614643546e-05,
|
| 163 |
+
"loss": 3.0261470794677736,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.8598130841121495,
|
| 168 |
+
"grad_norm": 3.5683584213256836,
|
| 169 |
+
"learning_rate": 1.1830443159922928e-05,
|
| 170 |
+
"loss": 2.9946710586547853,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.897196261682243,
|
| 175 |
+
"grad_norm": 4.219651699066162,
|
| 176 |
+
"learning_rate": 1.1445086705202313e-05,
|
| 177 |
+
"loss": 3.067545509338379,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.9345794392523364,
|
| 182 |
+
"grad_norm": 3.2647459506988525,
|
| 183 |
+
"learning_rate": 1.1059730250481697e-05,
|
| 184 |
+
"loss": 3.047348976135254,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.9719626168224299,
|
| 189 |
+
"grad_norm": 3.6350138187408447,
|
| 190 |
+
"learning_rate": 1.067437379576108e-05,
|
| 191 |
+
"loss": 3.044650077819824,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.0,
|
| 196 |
+
"eval_loss": 2.9178810119628906,
|
| 197 |
+
"eval_runtime": 22.6583,
|
| 198 |
+
"eval_samples_per_second": 41.927,
|
| 199 |
+
"eval_steps_per_second": 20.964,
|
| 200 |
+
"step": 268
|
| 201 |
+
}
|
| 202 |
+
],
|
| 203 |
+
"logging_steps": 10,
|
| 204 |
+
"max_steps": 536,
|
| 205 |
+
"num_input_tokens_seen": 0,
|
| 206 |
+
"num_train_epochs": 2,
|
| 207 |
+
"save_steps": 54,
|
| 208 |
+
"stateful_callbacks": {
|
| 209 |
+
"TrainerControl": {
|
| 210 |
+
"args": {
|
| 211 |
+
"should_epoch_stop": false,
|
| 212 |
+
"should_evaluate": false,
|
| 213 |
+
"should_log": false,
|
| 214 |
+
"should_save": true,
|
| 215 |
+
"should_training_stop": false
|
| 216 |
+
},
|
| 217 |
+
"attributes": {}
|
| 218 |
+
}
|
| 219 |
+
},
|
| 220 |
+
"total_flos": 2929569518592000.0,
|
| 221 |
+
"train_batch_size": 16,
|
| 222 |
+
"trial_name": null,
|
| 223 |
+
"trial_params": null
|
| 224 |
+
}
|
checkpoint-268/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69ba02ebc020a08cab59f0264bae91fda0aab3c401e5a8a0b392e62b7c992c84
|
| 3 |
+
size 5201
|
checkpoint-536/chat_template.jinja
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- for message in messages %}
|
| 2 |
+
{{- '<|im_start|>' + message['role'] + '\n' }}
|
| 3 |
+
{{- message['content'] + '<|im_end|>' }}
|
| 4 |
+
{%- endfor %}
|
| 5 |
+
{%- if add_generation_prompt %}
|
| 6 |
+
{{- '<|im_start|>assistant\n' }}
|
| 7 |
+
{%- endif %}
|
checkpoint-536/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 768,
|
| 17 |
+
"n_head": 12,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 12,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"pad_token_id": 50257,
|
| 22 |
+
"reorder_and_upcast_attn": false,
|
| 23 |
+
"resid_pdrop": 0.1,
|
| 24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
+
"scale_attn_weights": true,
|
| 26 |
+
"summary_activation": null,
|
| 27 |
+
"summary_first_dropout": 0.1,
|
| 28 |
+
"summary_proj_to_labels": true,
|
| 29 |
+
"summary_type": "cls_index",
|
| 30 |
+
"summary_use_proj": true,
|
| 31 |
+
"task_specific_params": {
|
| 32 |
+
"text-generation": {
|
| 33 |
+
"do_sample": true,
|
| 34 |
+
"max_length": 50
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"tie_word_embeddings": true,
|
| 38 |
+
"transformers_version": "5.12.1",
|
| 39 |
+
"use_cache": false,
|
| 40 |
+
"vocab_size": 50261
|
| 41 |
+
}
|
checkpoint-536/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
50256
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 50257,
|
| 8 |
+
"transformers_version": "5.12.1"
|
| 9 |
+
}
|
checkpoint-536/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2438459cc797ca456511bdec467b4b0956644b807c2e04f324b991d5e5b965fa
|
| 3 |
+
size 497786496
|
checkpoint-536/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:767cd682572984a58002f1251dc2ebd0ef33be9c01fa3316e33c46e02a7cc01d
|
| 3 |
+
size 995669387
|
checkpoint-536/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d77dd4d023f28adcce15c0875749bbb8f647951c27574602fb5679625ce2a24d
|
| 3 |
+
size 14645
|
checkpoint-536/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad4516b737034aa811e7b65bb87c80c15141083a7b865e96dc8bb27707d594fd
|
| 3 |
+
size 1465
|
checkpoint-536/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-536/tokenizer_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|endoftext|>",
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"extra_special_tokens": [
|
| 8 |
+
"<|im_start|>",
|
| 9 |
+
"<|im_end|>",
|
| 10 |
+
"<|im_sep|>"
|
| 11 |
+
],
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"local_files_only": false,
|
| 14 |
+
"model_max_length": 1024,
|
| 15 |
+
"pad_token": "<|pad|>",
|
| 16 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 17 |
+
"unk_token": "<|endoftext|>"
|
| 18 |
+
}
|
checkpoint-536/trainer_state.json
ADDED
|
@@ -0,0 +1,421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 536,
|
| 3 |
+
"best_metric": 2.8649895191192627,
|
| 4 |
+
"best_model_checkpoint": "gpt2-finetuned/checkpoint-536",
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 536,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.037383177570093455,
|
| 14 |
+
"grad_norm": 4.323858737945557,
|
| 15 |
+
"learning_rate": 1.0588235294117648e-05,
|
| 16 |
+
"loss": 3.5710372924804688,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.07476635514018691,
|
| 21 |
+
"grad_norm": 3.9307808876037598,
|
| 22 |
+
"learning_rate": 1.9922928709055876e-05,
|
| 23 |
+
"loss": 3.3915550231933596,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.11214953271028037,
|
| 28 |
+
"grad_norm": 3.703219175338745,
|
| 29 |
+
"learning_rate": 1.9537572254335264e-05,
|
| 30 |
+
"loss": 3.30927734375,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.14953271028037382,
|
| 35 |
+
"grad_norm": 3.3923251628875732,
|
| 36 |
+
"learning_rate": 1.9152215799614644e-05,
|
| 37 |
+
"loss": 3.2569236755371094,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.18691588785046728,
|
| 42 |
+
"grad_norm": 3.6839487552642822,
|
| 43 |
+
"learning_rate": 1.8766859344894028e-05,
|
| 44 |
+
"loss": 3.2078022003173827,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.22429906542056074,
|
| 49 |
+
"grad_norm": 3.1598305702209473,
|
| 50 |
+
"learning_rate": 1.838150289017341e-05,
|
| 51 |
+
"loss": 3.1958980560302734,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.2616822429906542,
|
| 56 |
+
"grad_norm": 3.5608792304992676,
|
| 57 |
+
"learning_rate": 1.7996146435452795e-05,
|
| 58 |
+
"loss": 3.1352081298828125,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.29906542056074764,
|
| 63 |
+
"grad_norm": 3.694288492202759,
|
| 64 |
+
"learning_rate": 1.761078998073218e-05,
|
| 65 |
+
"loss": 3.1180818557739256,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.3364485981308411,
|
| 70 |
+
"grad_norm": 3.2345361709594727,
|
| 71 |
+
"learning_rate": 1.722543352601156e-05,
|
| 72 |
+
"loss": 3.121156692504883,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.37383177570093457,
|
| 77 |
+
"grad_norm": 2.8083014488220215,
|
| 78 |
+
"learning_rate": 1.6840077071290947e-05,
|
| 79 |
+
"loss": 3.091750907897949,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.411214953271028,
|
| 84 |
+
"grad_norm": 3.5092177391052246,
|
| 85 |
+
"learning_rate": 1.645472061657033e-05,
|
| 86 |
+
"loss": 3.085820198059082,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.4485981308411215,
|
| 91 |
+
"grad_norm": 3.606647491455078,
|
| 92 |
+
"learning_rate": 1.606936416184971e-05,
|
| 93 |
+
"loss": 3.103367233276367,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.48598130841121495,
|
| 98 |
+
"grad_norm": 2.9848923683166504,
|
| 99 |
+
"learning_rate": 1.5684007707129095e-05,
|
| 100 |
+
"loss": 3.1185840606689452,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.5233644859813084,
|
| 105 |
+
"grad_norm": 3.9700093269348145,
|
| 106 |
+
"learning_rate": 1.529865125240848e-05,
|
| 107 |
+
"loss": 3.111907386779785,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.5607476635514018,
|
| 112 |
+
"grad_norm": 4.307053565979004,
|
| 113 |
+
"learning_rate": 1.4913294797687862e-05,
|
| 114 |
+
"loss": 3.1015724182128905,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.5981308411214953,
|
| 119 |
+
"grad_norm": 4.230574607849121,
|
| 120 |
+
"learning_rate": 1.4527938342967245e-05,
|
| 121 |
+
"loss": 3.1573991775512695,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.6355140186915887,
|
| 126 |
+
"grad_norm": 3.484198808670044,
|
| 127 |
+
"learning_rate": 1.414258188824663e-05,
|
| 128 |
+
"loss": 3.09665470123291,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.6728971962616822,
|
| 133 |
+
"grad_norm": 3.7458720207214355,
|
| 134 |
+
"learning_rate": 1.3757225433526014e-05,
|
| 135 |
+
"loss": 3.0797067642211915,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.7102803738317757,
|
| 140 |
+
"grad_norm": 3.599705457687378,
|
| 141 |
+
"learning_rate": 1.3371868978805396e-05,
|
| 142 |
+
"loss": 3.02014045715332,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.7476635514018691,
|
| 147 |
+
"grad_norm": 3.341883659362793,
|
| 148 |
+
"learning_rate": 1.298651252408478e-05,
|
| 149 |
+
"loss": 3.0037511825561523,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.7850467289719626,
|
| 154 |
+
"grad_norm": 3.6026880741119385,
|
| 155 |
+
"learning_rate": 1.2601156069364162e-05,
|
| 156 |
+
"loss": 2.995482063293457,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.822429906542056,
|
| 161 |
+
"grad_norm": 3.875734329223633,
|
| 162 |
+
"learning_rate": 1.2215799614643546e-05,
|
| 163 |
+
"loss": 3.0261470794677736,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.8598130841121495,
|
| 168 |
+
"grad_norm": 3.5683584213256836,
|
| 169 |
+
"learning_rate": 1.1830443159922928e-05,
|
| 170 |
+
"loss": 2.9946710586547853,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.897196261682243,
|
| 175 |
+
"grad_norm": 4.219651699066162,
|
| 176 |
+
"learning_rate": 1.1445086705202313e-05,
|
| 177 |
+
"loss": 3.067545509338379,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.9345794392523364,
|
| 182 |
+
"grad_norm": 3.2647459506988525,
|
| 183 |
+
"learning_rate": 1.1059730250481697e-05,
|
| 184 |
+
"loss": 3.047348976135254,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.9719626168224299,
|
| 189 |
+
"grad_norm": 3.6350138187408447,
|
| 190 |
+
"learning_rate": 1.067437379576108e-05,
|
| 191 |
+
"loss": 3.044650077819824,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.0,
|
| 196 |
+
"eval_loss": 2.9178810119628906,
|
| 197 |
+
"eval_runtime": 22.6583,
|
| 198 |
+
"eval_samples_per_second": 41.927,
|
| 199 |
+
"eval_steps_per_second": 20.964,
|
| 200 |
+
"step": 268
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.0074766355140188,
|
| 204 |
+
"grad_norm": 3.5870800018310547,
|
| 205 |
+
"learning_rate": 1.0289017341040463e-05,
|
| 206 |
+
"loss": 2.9937585830688476,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.0448598130841122,
|
| 211 |
+
"grad_norm": 4.361166000366211,
|
| 212 |
+
"learning_rate": 9.903660886319847e-06,
|
| 213 |
+
"loss": 3.0103271484375,
|
| 214 |
+
"step": 280
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.0822429906542057,
|
| 218 |
+
"grad_norm": 3.9424304962158203,
|
| 219 |
+
"learning_rate": 9.51830443159923e-06,
|
| 220 |
+
"loss": 2.9879344940185546,
|
| 221 |
+
"step": 290
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.1196261682242992,
|
| 225 |
+
"grad_norm": 4.069947719573975,
|
| 226 |
+
"learning_rate": 9.132947976878613e-06,
|
| 227 |
+
"loss": 2.987399673461914,
|
| 228 |
+
"step": 300
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.1570093457943926,
|
| 232 |
+
"grad_norm": 4.206397533416748,
|
| 233 |
+
"learning_rate": 8.747591522157996e-06,
|
| 234 |
+
"loss": 2.9407649993896485,
|
| 235 |
+
"step": 310
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.194392523364486,
|
| 239 |
+
"grad_norm": 4.135429382324219,
|
| 240 |
+
"learning_rate": 8.36223506743738e-06,
|
| 241 |
+
"loss": 2.9791286468505858,
|
| 242 |
+
"step": 320
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.2317757009345796,
|
| 246 |
+
"grad_norm": 4.783056259155273,
|
| 247 |
+
"learning_rate": 7.976878612716764e-06,
|
| 248 |
+
"loss": 2.982815742492676,
|
| 249 |
+
"step": 330
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.269158878504673,
|
| 253 |
+
"grad_norm": 4.636116981506348,
|
| 254 |
+
"learning_rate": 7.591522157996147e-06,
|
| 255 |
+
"loss": 3.0075199127197267,
|
| 256 |
+
"step": 340
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.3065420560747665,
|
| 260 |
+
"grad_norm": 4.425142765045166,
|
| 261 |
+
"learning_rate": 7.206165703275531e-06,
|
| 262 |
+
"loss": 3.0005060195922852,
|
| 263 |
+
"step": 350
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.34392523364486,
|
| 267 |
+
"grad_norm": 3.986107349395752,
|
| 268 |
+
"learning_rate": 6.820809248554914e-06,
|
| 269 |
+
"loss": 2.9552526473999023,
|
| 270 |
+
"step": 360
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.3813084112149534,
|
| 274 |
+
"grad_norm": 4.123307228088379,
|
| 275 |
+
"learning_rate": 6.435452793834297e-06,
|
| 276 |
+
"loss": 2.9348220825195312,
|
| 277 |
+
"step": 370
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.4186915887850469,
|
| 281 |
+
"grad_norm": 4.234403133392334,
|
| 282 |
+
"learning_rate": 6.0500963391136806e-06,
|
| 283 |
+
"loss": 2.963719940185547,
|
| 284 |
+
"step": 380
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.45607476635514,
|
| 288 |
+
"grad_norm": 5.90896463394165,
|
| 289 |
+
"learning_rate": 5.664739884393064e-06,
|
| 290 |
+
"loss": 2.98101749420166,
|
| 291 |
+
"step": 390
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.4934579439252336,
|
| 295 |
+
"grad_norm": 3.8738784790039062,
|
| 296 |
+
"learning_rate": 5.279383429672448e-06,
|
| 297 |
+
"loss": 2.9381120681762694,
|
| 298 |
+
"step": 400
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.5308411214953273,
|
| 302 |
+
"grad_norm": 4.2729268074035645,
|
| 303 |
+
"learning_rate": 4.894026974951831e-06,
|
| 304 |
+
"loss": 3.004109191894531,
|
| 305 |
+
"step": 410
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.5682242990654207,
|
| 309 |
+
"grad_norm": 4.344122886657715,
|
| 310 |
+
"learning_rate": 4.508670520231214e-06,
|
| 311 |
+
"loss": 2.8942329406738283,
|
| 312 |
+
"step": 420
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.6056074766355142,
|
| 316 |
+
"grad_norm": 4.170741081237793,
|
| 317 |
+
"learning_rate": 4.123314065510597e-06,
|
| 318 |
+
"loss": 2.9949222564697267,
|
| 319 |
+
"step": 430
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 1.6429906542056076,
|
| 323 |
+
"grad_norm": 4.825467109680176,
|
| 324 |
+
"learning_rate": 3.7379576107899813e-06,
|
| 325 |
+
"loss": 2.9415472030639647,
|
| 326 |
+
"step": 440
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.680373831775701,
|
| 330 |
+
"grad_norm": 4.231213569641113,
|
| 331 |
+
"learning_rate": 3.3526011560693642e-06,
|
| 332 |
+
"loss": 2.94517822265625,
|
| 333 |
+
"step": 450
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.7177570093457943,
|
| 337 |
+
"grad_norm": 4.937946319580078,
|
| 338 |
+
"learning_rate": 2.9672447013487476e-06,
|
| 339 |
+
"loss": 3.005815315246582,
|
| 340 |
+
"step": 460
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.7551401869158878,
|
| 344 |
+
"grad_norm": 4.124006748199463,
|
| 345 |
+
"learning_rate": 2.5818882466281314e-06,
|
| 346 |
+
"loss": 2.965633201599121,
|
| 347 |
+
"step": 470
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.7925233644859813,
|
| 351 |
+
"grad_norm": 3.962216854095459,
|
| 352 |
+
"learning_rate": 2.1965317919075148e-06,
|
| 353 |
+
"loss": 2.9793548583984375,
|
| 354 |
+
"step": 480
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.8299065420560747,
|
| 358 |
+
"grad_norm": 4.627573013305664,
|
| 359 |
+
"learning_rate": 1.8111753371868982e-06,
|
| 360 |
+
"loss": 2.9587646484375,
|
| 361 |
+
"step": 490
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.8672897196261682,
|
| 365 |
+
"grad_norm": 5.371633529663086,
|
| 366 |
+
"learning_rate": 1.4258188824662813e-06,
|
| 367 |
+
"loss": 2.9544118881225585,
|
| 368 |
+
"step": 500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.9046728971962616,
|
| 372 |
+
"grad_norm": 4.382261276245117,
|
| 373 |
+
"learning_rate": 1.040462427745665e-06,
|
| 374 |
+
"loss": 2.9408926010131835,
|
| 375 |
+
"step": 510
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.9420560747663551,
|
| 379 |
+
"grad_norm": 4.642389297485352,
|
| 380 |
+
"learning_rate": 6.551059730250482e-07,
|
| 381 |
+
"loss": 2.942763328552246,
|
| 382 |
+
"step": 520
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.9794392523364486,
|
| 386 |
+
"grad_norm": 4.728512763977051,
|
| 387 |
+
"learning_rate": 2.697495183044316e-07,
|
| 388 |
+
"loss": 2.9559442520141603,
|
| 389 |
+
"step": 530
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.0,
|
| 393 |
+
"eval_loss": 2.8649895191192627,
|
| 394 |
+
"eval_runtime": 22.662,
|
| 395 |
+
"eval_samples_per_second": 41.92,
|
| 396 |
+
"eval_steps_per_second": 20.96,
|
| 397 |
+
"step": 536
|
| 398 |
+
}
|
| 399 |
+
],
|
| 400 |
+
"logging_steps": 10,
|
| 401 |
+
"max_steps": 536,
|
| 402 |
+
"num_input_tokens_seen": 0,
|
| 403 |
+
"num_train_epochs": 2,
|
| 404 |
+
"save_steps": 54,
|
| 405 |
+
"stateful_callbacks": {
|
| 406 |
+
"TrainerControl": {
|
| 407 |
+
"args": {
|
| 408 |
+
"should_epoch_stop": false,
|
| 409 |
+
"should_evaluate": false,
|
| 410 |
+
"should_log": false,
|
| 411 |
+
"should_save": true,
|
| 412 |
+
"should_training_stop": true
|
| 413 |
+
},
|
| 414 |
+
"attributes": {}
|
| 415 |
+
}
|
| 416 |
+
},
|
| 417 |
+
"total_flos": 5813915102208000.0,
|
| 418 |
+
"train_batch_size": 16,
|
| 419 |
+
"trial_name": null,
|
| 420 |
+
"trial_params": null
|
| 421 |
+
}
|
checkpoint-536/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69ba02ebc020a08cab59f0264bae91fda0aab3c401e5a8a0b392e62b7c992c84
|
| 3 |
+
size 5201
|
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 768,
|
| 17 |
+
"n_head": 12,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 12,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"pad_token_id": 50257,
|
| 22 |
+
"reorder_and_upcast_attn": false,
|
| 23 |
+
"resid_pdrop": 0.1,
|
| 24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
+
"scale_attn_weights": true,
|
| 26 |
+
"summary_activation": null,
|
| 27 |
+
"summary_first_dropout": 0.1,
|
| 28 |
+
"summary_proj_to_labels": true,
|
| 29 |
+
"summary_type": "cls_index",
|
| 30 |
+
"summary_use_proj": true,
|
| 31 |
+
"task_specific_params": {
|
| 32 |
+
"text-generation": {
|
| 33 |
+
"do_sample": true,
|
| 34 |
+
"max_length": 50
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"tie_word_embeddings": true,
|
| 38 |
+
"transformers_version": "5.12.1",
|
| 39 |
+
"use_cache": false,
|
| 40 |
+
"vocab_size": 50261
|
| 41 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
50256
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 50257,
|
| 8 |
+
"transformers_version": "5.12.1"
|
| 9 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2438459cc797ca456511bdec467b4b0956644b807c2e04f324b991d5e5b965fa
|
| 3 |
+
size 497786496
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|endoftext|>",
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"extra_special_tokens": [
|
| 8 |
+
"<|im_start|>",
|
| 9 |
+
"<|im_end|>",
|
| 10 |
+
"<|im_sep|>"
|
| 11 |
+
],
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"local_files_only": false,
|
| 14 |
+
"model_max_length": 1024,
|
| 15 |
+
"pad_token": "<|pad|>",
|
| 16 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 17 |
+
"unk_token": "<|endoftext|>"
|
| 18 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69ba02ebc020a08cab59f0264bae91fda0aab3c401e5a8a0b392e62b7c992c84
|
| 3 |
+
size 5201
|