Figo
commited on
Commit
•
4ef8e25
1
Parent(s):
cf740ee
upload models
Browse files- config.json +73 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- trainer_state.json +376 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "EleutherAI/gpt-neo-1.3B",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPTNeoForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0,
|
| 8 |
+
"attention_layers": [
|
| 9 |
+
"global",
|
| 10 |
+
"local",
|
| 11 |
+
"global",
|
| 12 |
+
"local",
|
| 13 |
+
"global",
|
| 14 |
+
"local",
|
| 15 |
+
"global",
|
| 16 |
+
"local",
|
| 17 |
+
"global",
|
| 18 |
+
"local",
|
| 19 |
+
"global",
|
| 20 |
+
"local",
|
| 21 |
+
"global",
|
| 22 |
+
"local",
|
| 23 |
+
"global",
|
| 24 |
+
"local",
|
| 25 |
+
"global",
|
| 26 |
+
"local",
|
| 27 |
+
"global",
|
| 28 |
+
"local",
|
| 29 |
+
"global",
|
| 30 |
+
"local",
|
| 31 |
+
"global",
|
| 32 |
+
"local"
|
| 33 |
+
],
|
| 34 |
+
"attention_types": [
|
| 35 |
+
[
|
| 36 |
+
[
|
| 37 |
+
"global",
|
| 38 |
+
"local"
|
| 39 |
+
],
|
| 40 |
+
12
|
| 41 |
+
]
|
| 42 |
+
],
|
| 43 |
+
"bos_token_id": 50256,
|
| 44 |
+
"embed_dropout": 0,
|
| 45 |
+
"eos_token_id": 50256,
|
| 46 |
+
"gradient_checkpointing": false,
|
| 47 |
+
"hidden_size": 2048,
|
| 48 |
+
"initializer_range": 0.02,
|
| 49 |
+
"intermediate_size": null,
|
| 50 |
+
"layer_norm_epsilon": 1e-05,
|
| 51 |
+
"max_position_embeddings": 2048,
|
| 52 |
+
"model_type": "gpt_neo",
|
| 53 |
+
"num_heads": 16,
|
| 54 |
+
"num_layers": 24,
|
| 55 |
+
"resid_dropout": 0,
|
| 56 |
+
"summary_activation": null,
|
| 57 |
+
"summary_first_dropout": 0.1,
|
| 58 |
+
"summary_proj_to_labels": true,
|
| 59 |
+
"summary_type": "cls_index",
|
| 60 |
+
"summary_use_proj": true,
|
| 61 |
+
"task_specific_params": {
|
| 62 |
+
"text-generation": {
|
| 63 |
+
"do_sample": true,
|
| 64 |
+
"max_length": 50,
|
| 65 |
+
"temperature": 0.9
|
| 66 |
+
}
|
| 67 |
+
},
|
| 68 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 69 |
+
"transformers_version": "4.5.0",
|
| 70 |
+
"use_cache": true,
|
| 71 |
+
"vocab_size": 50258,
|
| 72 |
+
"window_size": 256
|
| 73 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cd0433018ac2f5ead3fb0fed842840d6888611fd947eb43fb55bac43a2cf59c
|
| 3 |
+
size 10524813825
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c98ac76318ab797a1edd3a5dcb19a5a554bc4e4e14eb9985bd66e5fc67d9f87
|
| 3 |
+
size 5312758285
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de9550b702c135ab43bae73e32128a0e9386927428d7e599cc5a80f5477345a1
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,376 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.2097819681791395,
|
| 5 |
+
"global_step": 15000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 2.5e-05,
|
| 13 |
+
"loss": 2.4058,
|
| 14 |
+
"step": 250
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.07,
|
| 18 |
+
"learning_rate": 5e-05,
|
| 19 |
+
"loss": 1.7915,
|
| 20 |
+
"step": 500
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.11,
|
| 24 |
+
"learning_rate": 4.981448501038884e-05,
|
| 25 |
+
"loss": 1.7151,
|
| 26 |
+
"step": 750
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.15,
|
| 30 |
+
"learning_rate": 4.9628970020777684e-05,
|
| 31 |
+
"loss": 1.6582,
|
| 32 |
+
"step": 1000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.18,
|
| 36 |
+
"learning_rate": 4.944345503116652e-05,
|
| 37 |
+
"loss": 1.634,
|
| 38 |
+
"step": 1250
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.22,
|
| 42 |
+
"learning_rate": 4.925794004155536e-05,
|
| 43 |
+
"loss": 1.6209,
|
| 44 |
+
"step": 1500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.26,
|
| 48 |
+
"learning_rate": 4.90724250519442e-05,
|
| 49 |
+
"loss": 1.6075,
|
| 50 |
+
"step": 1750
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.29,
|
| 54 |
+
"learning_rate": 4.888691006233304e-05,
|
| 55 |
+
"loss": 1.5856,
|
| 56 |
+
"step": 2000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.33,
|
| 60 |
+
"learning_rate": 4.870139507272188e-05,
|
| 61 |
+
"loss": 1.5721,
|
| 62 |
+
"step": 2250
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.37,
|
| 66 |
+
"learning_rate": 4.8515880083110716e-05,
|
| 67 |
+
"loss": 1.5656,
|
| 68 |
+
"step": 2500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.41,
|
| 72 |
+
"learning_rate": 4.833036509349956e-05,
|
| 73 |
+
"loss": 1.5553,
|
| 74 |
+
"step": 2750
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.44,
|
| 78 |
+
"learning_rate": 4.814485010388839e-05,
|
| 79 |
+
"loss": 1.5447,
|
| 80 |
+
"step": 3000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.48,
|
| 84 |
+
"learning_rate": 4.7959335114277236e-05,
|
| 85 |
+
"loss": 1.5448,
|
| 86 |
+
"step": 3250
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.52,
|
| 90 |
+
"learning_rate": 4.777382012466607e-05,
|
| 91 |
+
"loss": 1.5326,
|
| 92 |
+
"step": 3500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.55,
|
| 96 |
+
"learning_rate": 4.758830513505492e-05,
|
| 97 |
+
"loss": 1.5182,
|
| 98 |
+
"step": 3750
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.59,
|
| 102 |
+
"learning_rate": 4.7402790145443755e-05,
|
| 103 |
+
"loss": 1.5269,
|
| 104 |
+
"step": 4000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.63,
|
| 108 |
+
"learning_rate": 4.721727515583259e-05,
|
| 109 |
+
"loss": 1.5015,
|
| 110 |
+
"step": 4250
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.66,
|
| 114 |
+
"learning_rate": 4.703176016622143e-05,
|
| 115 |
+
"loss": 1.5099,
|
| 116 |
+
"step": 4500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.7,
|
| 120 |
+
"learning_rate": 4.684624517661027e-05,
|
| 121 |
+
"loss": 1.5057,
|
| 122 |
+
"step": 4750
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.74,
|
| 126 |
+
"learning_rate": 4.666073018699911e-05,
|
| 127 |
+
"loss": 1.5067,
|
| 128 |
+
"step": 5000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.77,
|
| 132 |
+
"learning_rate": 4.647521519738795e-05,
|
| 133 |
+
"loss": 1.4833,
|
| 134 |
+
"step": 5250
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.81,
|
| 138 |
+
"learning_rate": 4.6289700207776794e-05,
|
| 139 |
+
"loss": 1.4926,
|
| 140 |
+
"step": 5500
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.85,
|
| 144 |
+
"learning_rate": 4.610418521816563e-05,
|
| 145 |
+
"loss": 1.4981,
|
| 146 |
+
"step": 5750
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.88,
|
| 150 |
+
"learning_rate": 4.591867022855447e-05,
|
| 151 |
+
"loss": 1.4826,
|
| 152 |
+
"step": 6000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.92,
|
| 156 |
+
"learning_rate": 4.573315523894331e-05,
|
| 157 |
+
"loss": 1.4849,
|
| 158 |
+
"step": 6250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.96,
|
| 162 |
+
"learning_rate": 4.5547640249332144e-05,
|
| 163 |
+
"loss": 1.4865,
|
| 164 |
+
"step": 6500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.99,
|
| 168 |
+
"learning_rate": 4.536212525972099e-05,
|
| 169 |
+
"loss": 1.467,
|
| 170 |
+
"step": 6750
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.03,
|
| 174 |
+
"learning_rate": 4.5176610270109826e-05,
|
| 175 |
+
"loss": 1.3277,
|
| 176 |
+
"step": 7000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.07,
|
| 180 |
+
"learning_rate": 4.499109528049867e-05,
|
| 181 |
+
"loss": 1.2816,
|
| 182 |
+
"step": 7250
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.1,
|
| 186 |
+
"learning_rate": 4.480558029088751e-05,
|
| 187 |
+
"loss": 1.2934,
|
| 188 |
+
"step": 7500
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.14,
|
| 192 |
+
"learning_rate": 4.4620065301276345e-05,
|
| 193 |
+
"loss": 1.2981,
|
| 194 |
+
"step": 7750
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.18,
|
| 198 |
+
"learning_rate": 4.443455031166518e-05,
|
| 199 |
+
"loss": 1.2945,
|
| 200 |
+
"step": 8000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.22,
|
| 204 |
+
"learning_rate": 4.424903532205402e-05,
|
| 205 |
+
"loss": 1.2848,
|
| 206 |
+
"step": 8250
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.25,
|
| 210 |
+
"learning_rate": 4.4063520332442865e-05,
|
| 211 |
+
"loss": 1.2948,
|
| 212 |
+
"step": 8500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.29,
|
| 216 |
+
"learning_rate": 4.38780053428317e-05,
|
| 217 |
+
"loss": 1.2911,
|
| 218 |
+
"step": 8750
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.33,
|
| 222 |
+
"learning_rate": 4.369249035322055e-05,
|
| 223 |
+
"loss": 1.3008,
|
| 224 |
+
"step": 9000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.36,
|
| 228 |
+
"learning_rate": 4.3506975363609384e-05,
|
| 229 |
+
"loss": 1.3118,
|
| 230 |
+
"step": 9250
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.4,
|
| 234 |
+
"learning_rate": 4.332146037399822e-05,
|
| 235 |
+
"loss": 1.3036,
|
| 236 |
+
"step": 9500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.44,
|
| 240 |
+
"learning_rate": 4.313594538438706e-05,
|
| 241 |
+
"loss": 1.2999,
|
| 242 |
+
"step": 9750
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.47,
|
| 246 |
+
"learning_rate": 4.29504303947759e-05,
|
| 247 |
+
"loss": 1.2994,
|
| 248 |
+
"step": 10000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.51,
|
| 252 |
+
"learning_rate": 4.276491540516474e-05,
|
| 253 |
+
"loss": 1.2935,
|
| 254 |
+
"step": 10250
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.55,
|
| 258 |
+
"learning_rate": 4.257940041555358e-05,
|
| 259 |
+
"loss": 1.3001,
|
| 260 |
+
"step": 10500
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.58,
|
| 264 |
+
"learning_rate": 4.239388542594242e-05,
|
| 265 |
+
"loss": 1.3013,
|
| 266 |
+
"step": 10750
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.62,
|
| 270 |
+
"learning_rate": 4.2208370436331254e-05,
|
| 271 |
+
"loss": 1.3073,
|
| 272 |
+
"step": 11000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.66,
|
| 276 |
+
"learning_rate": 4.20228554467201e-05,
|
| 277 |
+
"loss": 1.3056,
|
| 278 |
+
"step": 11250
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.69,
|
| 282 |
+
"learning_rate": 4.1837340457108936e-05,
|
| 283 |
+
"loss": 1.3076,
|
| 284 |
+
"step": 11500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.73,
|
| 288 |
+
"learning_rate": 4.165182546749777e-05,
|
| 289 |
+
"loss": 1.2909,
|
| 290 |
+
"step": 11750
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.77,
|
| 294 |
+
"learning_rate": 4.146631047788662e-05,
|
| 295 |
+
"loss": 1.3034,
|
| 296 |
+
"step": 12000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.8,
|
| 300 |
+
"learning_rate": 4.1280795488275455e-05,
|
| 301 |
+
"loss": 1.2981,
|
| 302 |
+
"step": 12250
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.84,
|
| 306 |
+
"learning_rate": 4.109528049866429e-05,
|
| 307 |
+
"loss": 1.2989,
|
| 308 |
+
"step": 12500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.88,
|
| 312 |
+
"learning_rate": 4.090976550905313e-05,
|
| 313 |
+
"loss": 1.3018,
|
| 314 |
+
"step": 12750
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.92,
|
| 318 |
+
"learning_rate": 4.0724250519441975e-05,
|
| 319 |
+
"loss": 1.2971,
|
| 320 |
+
"step": 13000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.95,
|
| 324 |
+
"learning_rate": 4.053873552983081e-05,
|
| 325 |
+
"loss": 1.2975,
|
| 326 |
+
"step": 13250
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.99,
|
| 330 |
+
"learning_rate": 4.035322054021965e-05,
|
| 331 |
+
"loss": 1.2909,
|
| 332 |
+
"step": 13500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.03,
|
| 336 |
+
"learning_rate": 4.0167705550608494e-05,
|
| 337 |
+
"loss": 1.1078,
|
| 338 |
+
"step": 13750
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.06,
|
| 342 |
+
"learning_rate": 3.998219056099733e-05,
|
| 343 |
+
"loss": 0.9997,
|
| 344 |
+
"step": 14000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.1,
|
| 348 |
+
"learning_rate": 3.979667557138617e-05,
|
| 349 |
+
"loss": 1.0043,
|
| 350 |
+
"step": 14250
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.14,
|
| 354 |
+
"learning_rate": 3.961116058177501e-05,
|
| 355 |
+
"loss": 0.9951,
|
| 356 |
+
"step": 14500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.17,
|
| 360 |
+
"learning_rate": 3.942564559216385e-05,
|
| 361 |
+
"loss": 1.0098,
|
| 362 |
+
"step": 14750
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.21,
|
| 366 |
+
"learning_rate": 3.924013060255269e-05,
|
| 367 |
+
"loss": 1.0087,
|
| 368 |
+
"step": 15000
|
| 369 |
+
}
|
| 370 |
+
],
|
| 371 |
+
"max_steps": 67880,
|
| 372 |
+
"num_train_epochs": 10,
|
| 373 |
+
"total_flos": 2.462482633434071e+17,
|
| 374 |
+
"trial_name": null,
|
| 375 |
+
"trial_params": null
|
| 376 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef424c13f468059e01d5f06818397eb2475d35b9af476c8d539478d38e025fa2
|
| 3 |
+
size 2351
|