Commit
•
cbb162a
1
Parent(s):
14a56fe
Upload 10 files
Browse files- config.json +30 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +457 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "data/models/Mixtral-8x7B-v0.1",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MixtralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 256,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 256,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"model_type": "mixtral",
|
| 15 |
+
"num_attention_heads": 8,
|
| 16 |
+
"num_experts_per_tok": 1,
|
| 17 |
+
"num_hidden_layers": 8,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"num_local_experts": 64,
|
| 20 |
+
"output_router_logits": false,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_theta": 1000000.0,
|
| 23 |
+
"router_aux_loss_coef": 0.02,
|
| 24 |
+
"sliding_window": null,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.37.0.dev0",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 4096
|
| 30 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.37.0.dev0"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e90fd1b6cce1e2134e6f1ca98b8775490f0c9c4778f4476ced1263848545f53
|
| 3 |
+
size 420171272
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cbca065eb6b80f5d4370cfb563129ef642e3db7ceb00682b342c5a8c1716486
|
| 3 |
+
size 841300302
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fe25ef400b7da44284490d7c6549ffafd7b8dedbd6684750f0602e9e7a8915b
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b94ac265b91edf6758a6e0e6ffa8f19c5d987c73d2e5b89c88f79283586a211b
|
| 3 |
+
size 627
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"tokenizer_class": "PreTrainedTokenizerFast", "unk_token": "[UNK]", "cls_token": "[CLS]", "sep_token": "[SEP]", "pad_token": "[PAD]", "mask_token": "[MASK]"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,457 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 5.340388298034668,
|
| 3 |
+
"best_model_checkpoint": "./results/models/checkpoint-9325",
|
| 4 |
+
"epoch": 40.99982412944073,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 9325,
|
| 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 |
+
"eval_loss": 6.240943908691406,
|
| 14 |
+
"eval_runtime": 1306.4602,
|
| 15 |
+
"eval_samples_per_second": 2228.206,
|
| 16 |
+
"eval_steps_per_second": 2.176,
|
| 17 |
+
"step": 227
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 2.0,
|
| 21 |
+
"eval_loss": 5.840852737426758,
|
| 22 |
+
"eval_runtime": 1315.4788,
|
| 23 |
+
"eval_samples_per_second": 2212.93,
|
| 24 |
+
"eval_steps_per_second": 2.161,
|
| 25 |
+
"step": 454
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.2,
|
| 29 |
+
"learning_rate": 0.00047797356828193835,
|
| 30 |
+
"loss": 6.2671,
|
| 31 |
+
"step": 500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 3.0,
|
| 35 |
+
"eval_loss": 5.713865756988525,
|
| 36 |
+
"eval_runtime": 1312.4705,
|
| 37 |
+
"eval_samples_per_second": 2218.002,
|
| 38 |
+
"eval_steps_per_second": 2.166,
|
| 39 |
+
"step": 682
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 4.0,
|
| 43 |
+
"eval_loss": 5.635574817657471,
|
| 44 |
+
"eval_runtime": 1313.1826,
|
| 45 |
+
"eval_samples_per_second": 2216.799,
|
| 46 |
+
"eval_steps_per_second": 2.165,
|
| 47 |
+
"step": 909
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 4.4,
|
| 51 |
+
"learning_rate": 0.00045594713656387664,
|
| 52 |
+
"loss": 5.7007,
|
| 53 |
+
"step": 1000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 5.0,
|
| 57 |
+
"eval_loss": 5.646896839141846,
|
| 58 |
+
"eval_runtime": 1315.5043,
|
| 59 |
+
"eval_samples_per_second": 2212.887,
|
| 60 |
+
"eval_steps_per_second": 2.161,
|
| 61 |
+
"step": 1137
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 6.0,
|
| 65 |
+
"eval_loss": 5.588204383850098,
|
| 66 |
+
"eval_runtime": 1308.1379,
|
| 67 |
+
"eval_samples_per_second": 2225.348,
|
| 68 |
+
"eval_steps_per_second": 2.173,
|
| 69 |
+
"step": 1364
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 6.6,
|
| 73 |
+
"learning_rate": 0.000433920704845815,
|
| 74 |
+
"loss": 5.577,
|
| 75 |
+
"step": 1500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 7.0,
|
| 79 |
+
"eval_loss": 5.526153564453125,
|
| 80 |
+
"eval_runtime": 1313.5897,
|
| 81 |
+
"eval_samples_per_second": 2216.112,
|
| 82 |
+
"eval_steps_per_second": 2.164,
|
| 83 |
+
"step": 1592
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 8.0,
|
| 87 |
+
"eval_loss": 5.503279685974121,
|
| 88 |
+
"eval_runtime": 1319.9731,
|
| 89 |
+
"eval_samples_per_second": 2205.395,
|
| 90 |
+
"eval_steps_per_second": 2.154,
|
| 91 |
+
"step": 1819
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 8.79,
|
| 95 |
+
"learning_rate": 0.00041189427312775327,
|
| 96 |
+
"loss": 5.521,
|
| 97 |
+
"step": 2000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 9.0,
|
| 101 |
+
"eval_loss": 5.491898536682129,
|
| 102 |
+
"eval_runtime": 1312.4959,
|
| 103 |
+
"eval_samples_per_second": 2217.959,
|
| 104 |
+
"eval_steps_per_second": 2.166,
|
| 105 |
+
"step": 2046
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 10.0,
|
| 109 |
+
"eval_loss": 5.471615314483643,
|
| 110 |
+
"eval_runtime": 1334.8552,
|
| 111 |
+
"eval_samples_per_second": 2180.807,
|
| 112 |
+
"eval_steps_per_second": 2.13,
|
| 113 |
+
"step": 2274
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 10.99,
|
| 117 |
+
"learning_rate": 0.0003898678414096916,
|
| 118 |
+
"loss": 5.4662,
|
| 119 |
+
"step": 2500
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 11.0,
|
| 123 |
+
"eval_loss": 5.465639114379883,
|
| 124 |
+
"eval_runtime": 1311.5138,
|
| 125 |
+
"eval_samples_per_second": 2219.62,
|
| 126 |
+
"eval_steps_per_second": 2.168,
|
| 127 |
+
"step": 2501
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 12.0,
|
| 131 |
+
"eval_loss": 5.454081058502197,
|
| 132 |
+
"eval_runtime": 1331.8262,
|
| 133 |
+
"eval_samples_per_second": 2185.767,
|
| 134 |
+
"eval_steps_per_second": 2.135,
|
| 135 |
+
"step": 2729
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 13.0,
|
| 139 |
+
"eval_loss": 5.4356560707092285,
|
| 140 |
+
"eval_runtime": 1314.9113,
|
| 141 |
+
"eval_samples_per_second": 2213.885,
|
| 142 |
+
"eval_steps_per_second": 2.162,
|
| 143 |
+
"step": 2956
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 13.19,
|
| 147 |
+
"learning_rate": 0.00036784140969163,
|
| 148 |
+
"loss": 5.4335,
|
| 149 |
+
"step": 3000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 14.0,
|
| 153 |
+
"eval_loss": 5.438130855560303,
|
| 154 |
+
"eval_runtime": 1321.1785,
|
| 155 |
+
"eval_samples_per_second": 2203.383,
|
| 156 |
+
"eval_steps_per_second": 2.152,
|
| 157 |
+
"step": 3184
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 15.0,
|
| 161 |
+
"eval_loss": 5.445527076721191,
|
| 162 |
+
"eval_runtime": 1373.6525,
|
| 163 |
+
"eval_samples_per_second": 2119.213,
|
| 164 |
+
"eval_steps_per_second": 2.07,
|
| 165 |
+
"step": 3411
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 15.39,
|
| 169 |
+
"learning_rate": 0.0003458149779735683,
|
| 170 |
+
"loss": 5.4113,
|
| 171 |
+
"step": 3500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 16.0,
|
| 175 |
+
"eval_loss": 5.419914722442627,
|
| 176 |
+
"eval_runtime": 1306.18,
|
| 177 |
+
"eval_samples_per_second": 2228.684,
|
| 178 |
+
"eval_steps_per_second": 2.177,
|
| 179 |
+
"step": 3639
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 17.0,
|
| 183 |
+
"eval_loss": 5.416874885559082,
|
| 184 |
+
"eval_runtime": 1324.9112,
|
| 185 |
+
"eval_samples_per_second": 2197.175,
|
| 186 |
+
"eval_steps_per_second": 2.146,
|
| 187 |
+
"step": 3866
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 17.59,
|
| 191 |
+
"learning_rate": 0.00032378854625550663,
|
| 192 |
+
"loss": 5.3891,
|
| 193 |
+
"step": 4000
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 18.0,
|
| 197 |
+
"eval_loss": 5.415682315826416,
|
| 198 |
+
"eval_runtime": 1305.4824,
|
| 199 |
+
"eval_samples_per_second": 2229.875,
|
| 200 |
+
"eval_steps_per_second": 2.178,
|
| 201 |
+
"step": 4093
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 19.0,
|
| 205 |
+
"eval_loss": 5.391342639923096,
|
| 206 |
+
"eval_runtime": 1304.433,
|
| 207 |
+
"eval_samples_per_second": 2231.669,
|
| 208 |
+
"eval_steps_per_second": 2.179,
|
| 209 |
+
"step": 4321
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 19.79,
|
| 213 |
+
"learning_rate": 0.000301762114537445,
|
| 214 |
+
"loss": 5.3728,
|
| 215 |
+
"step": 4500
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 20.0,
|
| 219 |
+
"eval_loss": 5.3856120109558105,
|
| 220 |
+
"eval_runtime": 1316.8368,
|
| 221 |
+
"eval_samples_per_second": 2210.648,
|
| 222 |
+
"eval_steps_per_second": 2.159,
|
| 223 |
+
"step": 4548
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 21.0,
|
| 227 |
+
"eval_loss": 5.4083051681518555,
|
| 228 |
+
"eval_runtime": 1315.5537,
|
| 229 |
+
"eval_samples_per_second": 2212.804,
|
| 230 |
+
"eval_steps_per_second": 2.161,
|
| 231 |
+
"step": 4776
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 21.98,
|
| 235 |
+
"learning_rate": 0.00027973568281938326,
|
| 236 |
+
"loss": 5.3561,
|
| 237 |
+
"step": 5000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 22.0,
|
| 241 |
+
"eval_loss": 5.3793134689331055,
|
| 242 |
+
"eval_runtime": 1313.7832,
|
| 243 |
+
"eval_samples_per_second": 2215.786,
|
| 244 |
+
"eval_steps_per_second": 2.164,
|
| 245 |
+
"step": 5003
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 23.0,
|
| 249 |
+
"eval_loss": 5.421042442321777,
|
| 250 |
+
"eval_runtime": 1337.1348,
|
| 251 |
+
"eval_samples_per_second": 2177.089,
|
| 252 |
+
"eval_steps_per_second": 2.126,
|
| 253 |
+
"step": 5231
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 24.0,
|
| 257 |
+
"eval_loss": 5.371836185455322,
|
| 258 |
+
"eval_runtime": 1305.6324,
|
| 259 |
+
"eval_samples_per_second": 2229.618,
|
| 260 |
+
"eval_steps_per_second": 2.177,
|
| 261 |
+
"step": 5458
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 24.18,
|
| 265 |
+
"learning_rate": 0.0002577092511013216,
|
| 266 |
+
"loss": 5.3458,
|
| 267 |
+
"step": 5500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 25.0,
|
| 271 |
+
"eval_loss": 5.3682403564453125,
|
| 272 |
+
"eval_runtime": 1309.0037,
|
| 273 |
+
"eval_samples_per_second": 2223.876,
|
| 274 |
+
"eval_steps_per_second": 2.172,
|
| 275 |
+
"step": 5686
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 26.0,
|
| 279 |
+
"eval_loss": 5.368312358856201,
|
| 280 |
+
"eval_runtime": 1303.9762,
|
| 281 |
+
"eval_samples_per_second": 2232.45,
|
| 282 |
+
"eval_steps_per_second": 2.18,
|
| 283 |
+
"step": 5913
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 26.38,
|
| 287 |
+
"learning_rate": 0.00023568281938325992,
|
| 288 |
+
"loss": 5.3355,
|
| 289 |
+
"step": 6000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 27.0,
|
| 293 |
+
"eval_loss": 5.381237983703613,
|
| 294 |
+
"eval_runtime": 1308.1689,
|
| 295 |
+
"eval_samples_per_second": 2225.295,
|
| 296 |
+
"eval_steps_per_second": 2.173,
|
| 297 |
+
"step": 6140
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 28.0,
|
| 301 |
+
"eval_loss": 5.359594821929932,
|
| 302 |
+
"eval_runtime": 1327.0099,
|
| 303 |
+
"eval_samples_per_second": 2193.7,
|
| 304 |
+
"eval_steps_per_second": 2.142,
|
| 305 |
+
"step": 6368
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 28.58,
|
| 309 |
+
"learning_rate": 0.00021365638766519823,
|
| 310 |
+
"loss": 5.325,
|
| 311 |
+
"step": 6500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 29.0,
|
| 315 |
+
"eval_loss": 5.356747627258301,
|
| 316 |
+
"eval_runtime": 1307.1198,
|
| 317 |
+
"eval_samples_per_second": 2227.081,
|
| 318 |
+
"eval_steps_per_second": 2.175,
|
| 319 |
+
"step": 6595
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 30.0,
|
| 323 |
+
"eval_loss": 5.362793922424316,
|
| 324 |
+
"eval_runtime": 1308.9269,
|
| 325 |
+
"eval_samples_per_second": 2224.007,
|
| 326 |
+
"eval_steps_per_second": 2.172,
|
| 327 |
+
"step": 6823
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 30.78,
|
| 331 |
+
"learning_rate": 0.00019162995594713657,
|
| 332 |
+
"loss": 5.3152,
|
| 333 |
+
"step": 7000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 31.0,
|
| 337 |
+
"eval_loss": 5.352448463439941,
|
| 338 |
+
"eval_runtime": 1309.5201,
|
| 339 |
+
"eval_samples_per_second": 2222.999,
|
| 340 |
+
"eval_steps_per_second": 2.171,
|
| 341 |
+
"step": 7050
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 32.0,
|
| 345 |
+
"eval_loss": 5.350729942321777,
|
| 346 |
+
"eval_runtime": 1330.3256,
|
| 347 |
+
"eval_samples_per_second": 2188.233,
|
| 348 |
+
"eval_steps_per_second": 2.137,
|
| 349 |
+
"step": 7278
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 32.98,
|
| 353 |
+
"learning_rate": 0.0001696035242290749,
|
| 354 |
+
"loss": 5.308,
|
| 355 |
+
"step": 7500
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 33.0,
|
| 359 |
+
"eval_loss": 5.350089073181152,
|
| 360 |
+
"eval_runtime": 1308.4994,
|
| 361 |
+
"eval_samples_per_second": 2224.733,
|
| 362 |
+
"eval_steps_per_second": 2.173,
|
| 363 |
+
"step": 7505
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 34.0,
|
| 367 |
+
"eval_loss": 5.350754261016846,
|
| 368 |
+
"eval_runtime": 1309.6607,
|
| 369 |
+
"eval_samples_per_second": 2222.76,
|
| 370 |
+
"eval_steps_per_second": 2.171,
|
| 371 |
+
"step": 7732
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 35.0,
|
| 375 |
+
"eval_loss": 5.346126556396484,
|
| 376 |
+
"eval_runtime": 1313.4913,
|
| 377 |
+
"eval_samples_per_second": 2216.278,
|
| 378 |
+
"eval_steps_per_second": 2.164,
|
| 379 |
+
"step": 7960
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 35.17,
|
| 383 |
+
"learning_rate": 0.00014757709251101323,
|
| 384 |
+
"loss": 5.2995,
|
| 385 |
+
"step": 8000
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 36.0,
|
| 389 |
+
"eval_loss": 5.345256805419922,
|
| 390 |
+
"eval_runtime": 1308.5486,
|
| 391 |
+
"eval_samples_per_second": 2224.65,
|
| 392 |
+
"eval_steps_per_second": 2.173,
|
| 393 |
+
"step": 8187
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 37.0,
|
| 397 |
+
"eval_loss": 5.342759132385254,
|
| 398 |
+
"eval_runtime": 1310.0897,
|
| 399 |
+
"eval_samples_per_second": 2222.033,
|
| 400 |
+
"eval_steps_per_second": 2.17,
|
| 401 |
+
"step": 8415
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 37.37,
|
| 405 |
+
"learning_rate": 0.00012555066079295154,
|
| 406 |
+
"loss": 5.2925,
|
| 407 |
+
"step": 8500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 38.0,
|
| 411 |
+
"eval_loss": 5.342674255371094,
|
| 412 |
+
"eval_runtime": 1309.6934,
|
| 413 |
+
"eval_samples_per_second": 2222.705,
|
| 414 |
+
"eval_steps_per_second": 2.171,
|
| 415 |
+
"step": 8642
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 39.0,
|
| 419 |
+
"eval_loss": 5.3418426513671875,
|
| 420 |
+
"eval_runtime": 1305.0501,
|
| 421 |
+
"eval_samples_per_second": 2230.613,
|
| 422 |
+
"eval_steps_per_second": 2.178,
|
| 423 |
+
"step": 8870
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 39.57,
|
| 427 |
+
"learning_rate": 0.00010352422907488987,
|
| 428 |
+
"loss": 5.2885,
|
| 429 |
+
"step": 9000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 40.0,
|
| 433 |
+
"eval_loss": 5.341084957122803,
|
| 434 |
+
"eval_runtime": 1304.7409,
|
| 435 |
+
"eval_samples_per_second": 2231.142,
|
| 436 |
+
"eval_steps_per_second": 2.179,
|
| 437 |
+
"step": 9097
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 41.0,
|
| 441 |
+
"eval_loss": 5.340388298034668,
|
| 442 |
+
"eval_runtime": 1304.8663,
|
| 443 |
+
"eval_samples_per_second": 2230.927,
|
| 444 |
+
"eval_steps_per_second": 2.179,
|
| 445 |
+
"step": 9325
|
| 446 |
+
}
|
| 447 |
+
],
|
| 448 |
+
"logging_steps": 500,
|
| 449 |
+
"max_steps": 11350,
|
| 450 |
+
"num_input_tokens_seen": 0,
|
| 451 |
+
"num_train_epochs": 50,
|
| 452 |
+
"save_steps": 500,
|
| 453 |
+
"total_flos": 1.6473372597391884e+19,
|
| 454 |
+
"train_batch_size": 1024,
|
| 455 |
+
"trial_name": null,
|
| 456 |
+
"trial_params": null
|
| 457 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ee188095cc0ad6e726a205eb1235ccc135ed86505ff509f635489e62e4cf3f8
|
| 3 |
+
size 4219
|