Commit
•
5384620
1
Parent(s):
94817f6
Upload 13 files
Browse files- config.json +38 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +19 -0
- trainer_state.json +405 -0
- training_args.bin +3 -0
- vocab.json +0 -0
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 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_ctx": 512,
|
| 14 |
+
"n_embd": 1280,
|
| 15 |
+
"n_head": 20,
|
| 16 |
+
"n_inner": null,
|
| 17 |
+
"n_layer": 36,
|
| 18 |
+
"n_positions": 512,
|
| 19 |
+
"reorder_and_upcast_attn": false,
|
| 20 |
+
"resid_pdrop": 0.1,
|
| 21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 22 |
+
"scale_attn_weights": true,
|
| 23 |
+
"summary_activation": null,
|
| 24 |
+
"summary_first_dropout": 0.1,
|
| 25 |
+
"summary_proj_to_labels": true,
|
| 26 |
+
"summary_type": "cls_index",
|
| 27 |
+
"summary_use_proj": true,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"text-generation": {
|
| 30 |
+
"do_sample": true,
|
| 31 |
+
"max_length": 50
|
| 32 |
+
}
|
| 33 |
+
},
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.38.0.dev0",
|
| 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": "4.38.0.dev0"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:432b1fcf838e744ab92246af8975255f8f88397d9013e48e96a67de0f7b887fd
|
| 3 |
+
size 6187371110
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83efc02be5dd066c4df3862ce7061530b5296a3e98eaa86136af94375c76d119
|
| 3 |
+
size 3093641690
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9358864fede1d786eb68265d573d146218415b252edbafe539bcf9169f310616
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aadc484524497cadf70ab3be9c3164856e54f23021a869a7dfc4594622d7d9a2
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"model_max_length": 1024,
|
| 17 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 18 |
+
"unk_token": "<|endoftext|>"
|
| 19 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,405 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.29740163905478323,
|
| 5 |
+
"eval_steps": 100000000,
|
| 6 |
+
"global_step": 32000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 5e-05,
|
| 14 |
+
"loss": 7.7296,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"learning_rate": 4.9999535305620204e-05,
|
| 20 |
+
"loss": 6.5786,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.0,
|
| 25 |
+
"learning_rate": 4.99990706112404e-05,
|
| 26 |
+
"loss": 6.2317,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.0,
|
| 31 |
+
"learning_rate": 4.99986059168606e-05,
|
| 32 |
+
"loss": 6.0053,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.0,
|
| 37 |
+
"learning_rate": 4.99981412224808e-05,
|
| 38 |
+
"loss": 5.8615,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.0,
|
| 43 |
+
"learning_rate": 4.9997676528101e-05,
|
| 44 |
+
"loss": 5.6794,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0,
|
| 49 |
+
"learning_rate": 4.99972118337212e-05,
|
| 50 |
+
"loss": 5.5481,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0,
|
| 55 |
+
"learning_rate": 4.9996747139341396e-05,
|
| 56 |
+
"loss": 5.4375,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.0,
|
| 61 |
+
"learning_rate": 4.99962824449616e-05,
|
| 62 |
+
"loss": 5.3391,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.0,
|
| 67 |
+
"learning_rate": 4.99958177505818e-05,
|
| 68 |
+
"loss": 5.2598,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.01,
|
| 73 |
+
"learning_rate": 4.9995353056202e-05,
|
| 74 |
+
"loss": 5.17,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.01,
|
| 79 |
+
"learning_rate": 4.9994888361822204e-05,
|
| 80 |
+
"loss": 5.0886,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.01,
|
| 85 |
+
"learning_rate": 4.99944236674424e-05,
|
| 86 |
+
"loss": 5.0128,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.01,
|
| 91 |
+
"learning_rate": 4.99939589730626e-05,
|
| 92 |
+
"loss": 4.9504,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.01,
|
| 97 |
+
"learning_rate": 4.99934942786828e-05,
|
| 98 |
+
"loss": 4.8755,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.01,
|
| 103 |
+
"learning_rate": 4.9993029584303e-05,
|
| 104 |
+
"loss": 4.8402,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.01,
|
| 109 |
+
"learning_rate": 4.99925648899232e-05,
|
| 110 |
+
"loss": 4.7674,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.01,
|
| 115 |
+
"learning_rate": 4.9992100195543396e-05,
|
| 116 |
+
"loss": 4.7254,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.01,
|
| 121 |
+
"learning_rate": 4.99916355011636e-05,
|
| 122 |
+
"loss": 4.6749,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.01,
|
| 127 |
+
"learning_rate": 4.99911708067838e-05,
|
| 128 |
+
"loss": 4.6135,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.01,
|
| 133 |
+
"learning_rate": 4.9990706112403995e-05,
|
| 134 |
+
"loss": 4.5239,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.01,
|
| 139 |
+
"learning_rate": 4.99902414180242e-05,
|
| 140 |
+
"loss": 4.4729,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.01,
|
| 145 |
+
"learning_rate": 4.998977672364439e-05,
|
| 146 |
+
"loss": 4.4434,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.01,
|
| 151 |
+
"learning_rate": 4.9989312029264594e-05,
|
| 152 |
+
"loss": 4.3587,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.01,
|
| 157 |
+
"learning_rate": 4.9988847334884796e-05,
|
| 158 |
+
"loss": 4.3126,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.01,
|
| 163 |
+
"learning_rate": 4.998838264050499e-05,
|
| 164 |
+
"loss": 4.2658,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.01,
|
| 169 |
+
"learning_rate": 4.998791794612519e-05,
|
| 170 |
+
"loss": 4.2412,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.01,
|
| 175 |
+
"learning_rate": 4.9987453251745395e-05,
|
| 176 |
+
"loss": 4.2035,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.01,
|
| 181 |
+
"learning_rate": 4.998698855736559e-05,
|
| 182 |
+
"loss": 4.1695,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.01,
|
| 187 |
+
"learning_rate": 4.998652386298579e-05,
|
| 188 |
+
"loss": 4.1406,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.01,
|
| 193 |
+
"learning_rate": 4.9986059168605994e-05,
|
| 194 |
+
"loss": 4.1275,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.01,
|
| 199 |
+
"learning_rate": 4.9985594474226196e-05,
|
| 200 |
+
"loss": 4.1032,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.02,
|
| 205 |
+
"learning_rate": 4.99851297798464e-05,
|
| 206 |
+
"loss": 4.0588,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.02,
|
| 211 |
+
"learning_rate": 4.9984665085466594e-05,
|
| 212 |
+
"loss": 4.0536,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.02,
|
| 217 |
+
"learning_rate": 4.9984200391086796e-05,
|
| 218 |
+
"loss": 3.9979,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.02,
|
| 223 |
+
"learning_rate": 4.998373569670699e-05,
|
| 224 |
+
"loss": 3.9913,
|
| 225 |
+
"step": 18000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.02,
|
| 229 |
+
"learning_rate": 4.998327100232719e-05,
|
| 230 |
+
"loss": 3.988,
|
| 231 |
+
"step": 18500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.02,
|
| 235 |
+
"learning_rate": 4.9982806307947395e-05,
|
| 236 |
+
"loss": 3.9575,
|
| 237 |
+
"step": 19000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.02,
|
| 241 |
+
"learning_rate": 4.998234161356759e-05,
|
| 242 |
+
"loss": 3.942,
|
| 243 |
+
"step": 19500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.02,
|
| 247 |
+
"learning_rate": 4.998187691918779e-05,
|
| 248 |
+
"loss": 3.9258,
|
| 249 |
+
"step": 20000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.02,
|
| 253 |
+
"learning_rate": 4.998141222480799e-05,
|
| 254 |
+
"loss": 3.8736,
|
| 255 |
+
"step": 20500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.02,
|
| 259 |
+
"learning_rate": 4.998094753042819e-05,
|
| 260 |
+
"loss": 3.903,
|
| 261 |
+
"step": 21000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2,
|
| 265 |
+
"learning_rate": 4.9804810945458605e-05,
|
| 266 |
+
"loss": 3.7108,
|
| 267 |
+
"step": 21500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.2,
|
| 271 |
+
"learning_rate": 4.980016358701714e-05,
|
| 272 |
+
"loss": 3.6276,
|
| 273 |
+
"step": 22000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.21,
|
| 277 |
+
"learning_rate": 4.979551622857568e-05,
|
| 278 |
+
"loss": 3.568,
|
| 279 |
+
"step": 22500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.21,
|
| 283 |
+
"learning_rate": 4.9790868870134216e-05,
|
| 284 |
+
"loss": 3.5307,
|
| 285 |
+
"step": 23000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.22,
|
| 289 |
+
"learning_rate": 4.978622151169275e-05,
|
| 290 |
+
"loss": 3.4857,
|
| 291 |
+
"step": 23500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.22,
|
| 295 |
+
"learning_rate": 4.978157415325129e-05,
|
| 296 |
+
"loss": 3.4463,
|
| 297 |
+
"step": 24000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.23,
|
| 301 |
+
"learning_rate": 4.977692679480983e-05,
|
| 302 |
+
"loss": 3.4396,
|
| 303 |
+
"step": 24500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.23,
|
| 307 |
+
"learning_rate": 4.977227943636837e-05,
|
| 308 |
+
"loss": 3.402,
|
| 309 |
+
"step": 25000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.24,
|
| 313 |
+
"learning_rate": 4.9767632077926904e-05,
|
| 314 |
+
"loss": 3.3716,
|
| 315 |
+
"step": 25500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.24,
|
| 319 |
+
"learning_rate": 4.9762984719485446e-05,
|
| 320 |
+
"loss": 3.3533,
|
| 321 |
+
"step": 26000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.25,
|
| 325 |
+
"learning_rate": 4.975833736104398e-05,
|
| 326 |
+
"loss": 3.3084,
|
| 327 |
+
"step": 26500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.25,
|
| 331 |
+
"learning_rate": 4.975369000260252e-05,
|
| 332 |
+
"loss": 3.293,
|
| 333 |
+
"step": 27000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.26,
|
| 337 |
+
"learning_rate": 4.974904264416106e-05,
|
| 338 |
+
"loss": 3.2707,
|
| 339 |
+
"step": 27500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.26,
|
| 343 |
+
"learning_rate": 4.97443952857196e-05,
|
| 344 |
+
"loss": 3.2561,
|
| 345 |
+
"step": 28000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 4.9739747927278134e-05,
|
| 350 |
+
"loss": 3.2219,
|
| 351 |
+
"step": 28500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.27,
|
| 355 |
+
"learning_rate": 4.9735100568836676e-05,
|
| 356 |
+
"loss": 3.2014,
|
| 357 |
+
"step": 29000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.27,
|
| 361 |
+
"learning_rate": 4.973045321039521e-05,
|
| 362 |
+
"loss": 3.1892,
|
| 363 |
+
"step": 29500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.28,
|
| 367 |
+
"learning_rate": 4.972580585195375e-05,
|
| 368 |
+
"loss": 3.1734,
|
| 369 |
+
"step": 30000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.28,
|
| 373 |
+
"learning_rate": 4.972115849351229e-05,
|
| 374 |
+
"loss": 3.1624,
|
| 375 |
+
"step": 30500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.29,
|
| 379 |
+
"learning_rate": 4.971651113507082e-05,
|
| 380 |
+
"loss": 3.1416,
|
| 381 |
+
"step": 31000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.29,
|
| 385 |
+
"learning_rate": 4.9711863776629364e-05,
|
| 386 |
+
"loss": 3.1255,
|
| 387 |
+
"step": 31500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.3,
|
| 391 |
+
"learning_rate": 4.97072164181879e-05,
|
| 392 |
+
"loss": 3.1074,
|
| 393 |
+
"step": 32000
|
| 394 |
+
}
|
| 395 |
+
],
|
| 396 |
+
"logging_steps": 500,
|
| 397 |
+
"max_steps": 5379900,
|
| 398 |
+
"num_input_tokens_seen": 0,
|
| 399 |
+
"num_train_epochs": 50,
|
| 400 |
+
"save_steps": 1000,
|
| 401 |
+
"total_flos": 1.9955527581696e+18,
|
| 402 |
+
"train_batch_size": 7,
|
| 403 |
+
"trial_name": null,
|
| 404 |
+
"trial_params": null
|
| 405 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a960ed41d5ecec621c0f76c1daa338a1e73fa6de425d2fddaa8aaff71518aaf3
|
| 3 |
+
size 4664
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|