Training in progress, step 250, checkpoint
Browse files- checkpoint-250/config.json +28 -0
- checkpoint-250/generation_config.json +7 -0
- checkpoint-250/optimizer.pt +3 -0
- checkpoint-250/pytorch_model.bin +3 -0
- checkpoint-250/rng_state.pth +3 -0
- checkpoint-250/scheduler.pt +3 -0
- checkpoint-250/special_tokens_map.json +5 -0
- checkpoint-250/tokenizer.json +0 -0
- checkpoint-250/tokenizer_config.json +12 -0
- checkpoint-250/trainer_state.json +369 -0
- checkpoint-250/training_args.bin +3 -0
checkpoint-250/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_remove_final_layer_norm": false,
|
| 3 |
+
"activation_function": "relu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"OPTForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 2,
|
| 9 |
+
"do_layer_norm_before": true,
|
| 10 |
+
"dropout": 0.1,
|
| 11 |
+
"enable_bias": true,
|
| 12 |
+
"eos_token_id": 2,
|
| 13 |
+
"ffn_dim": 768,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"init_std": 0.02,
|
| 16 |
+
"layer_norm_elementwise_affine": true,
|
| 17 |
+
"layerdrop": 0.0,
|
| 18 |
+
"max_position_embeddings": 512,
|
| 19 |
+
"model_type": "opt",
|
| 20 |
+
"num_attention_heads": 8,
|
| 21 |
+
"num_hidden_layers": 8,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.33.3",
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 50002,
|
| 27 |
+
"word_embed_proj_dim": 768
|
| 28 |
+
}
|
checkpoint-250/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 1,
|
| 6 |
+
"transformers_version": "4.33.3"
|
| 7 |
+
}
|
checkpoint-250/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02dbf4fb1682650ef9b1fdb84a249e561a4724f5c956d6b1acd83ca81c3012e4
|
| 3 |
+
size 537476677
|
checkpoint-250/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e411396b4651e31ae336e08545778f107c8d02f28f2f75c49d898cc2ad5f7e34
|
| 3 |
+
size 268727709
|
checkpoint-250/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdf168a334f58bc5282e8e8861d89c72de1c570b30c1769ace3b1cc797b5bcff
|
| 3 |
+
size 14575
|
checkpoint-250/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a71e3c5829701508191c7ae9e7df7bfc2332fb7c335481998596ed84ef0c0a48
|
| 3 |
+
size 627
|
checkpoint-250/special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "<eos>",
|
| 3 |
+
"pad_token": "<pad>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
checkpoint-250/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-250/tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"eos_token": "<eos>",
|
| 4 |
+
"max_length": null,
|
| 5 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
+
"pad_to_multiple_of": null,
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"pad_token_type_id": 0,
|
| 9 |
+
"padding_side": "right",
|
| 10 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 11 |
+
"unk_token": "<unk>"
|
| 12 |
+
}
|
checkpoint-250/trainer_state.json
ADDED
|
@@ -0,0 +1,369 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 6.402657508850098,
|
| 3 |
+
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/lm-training/src/outputs/2023-11-15/09-23-00/checkpoints/checkpoint-250",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 10,
|
| 6 |
+
"global_step": 250,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"learning_rate": 4.866666666666667e-05,
|
| 14 |
+
"loss": 9.9717,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.08,
|
| 19 |
+
"eval_loss": 9.324381828308105,
|
| 20 |
+
"eval_runtime": 2.0042,
|
| 21 |
+
"eval_samples_per_second": 498.949,
|
| 22 |
+
"eval_steps_per_second": 62.369,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.16,
|
| 27 |
+
"learning_rate": 4.7333333333333336e-05,
|
| 28 |
+
"loss": 9.1002,
|
| 29 |
+
"step": 20
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.16,
|
| 33 |
+
"eval_loss": 8.892333984375,
|
| 34 |
+
"eval_runtime": 1.9424,
|
| 35 |
+
"eval_samples_per_second": 514.829,
|
| 36 |
+
"eval_steps_per_second": 64.354,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.24,
|
| 41 |
+
"learning_rate": 4.600000000000001e-05,
|
| 42 |
+
"loss": 8.7625,
|
| 43 |
+
"step": 30
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.24,
|
| 47 |
+
"eval_loss": 8.54922103881836,
|
| 48 |
+
"eval_runtime": 1.9052,
|
| 49 |
+
"eval_samples_per_second": 524.878,
|
| 50 |
+
"eval_steps_per_second": 65.61,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.32,
|
| 55 |
+
"learning_rate": 4.466666666666667e-05,
|
| 56 |
+
"loss": 8.4987,
|
| 57 |
+
"step": 40
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.32,
|
| 61 |
+
"eval_loss": 8.234408378601074,
|
| 62 |
+
"eval_runtime": 2.0895,
|
| 63 |
+
"eval_samples_per_second": 478.585,
|
| 64 |
+
"eval_steps_per_second": 59.823,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.4,
|
| 69 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 70 |
+
"loss": 8.2485,
|
| 71 |
+
"step": 50
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.4,
|
| 75 |
+
"eval_loss": 7.941398620605469,
|
| 76 |
+
"eval_runtime": 2.1108,
|
| 77 |
+
"eval_samples_per_second": 473.76,
|
| 78 |
+
"eval_steps_per_second": 59.22,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.48,
|
| 83 |
+
"learning_rate": 4.2e-05,
|
| 84 |
+
"loss": 8.0802,
|
| 85 |
+
"step": 60
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.48,
|
| 89 |
+
"eval_loss": 7.663424968719482,
|
| 90 |
+
"eval_runtime": 1.991,
|
| 91 |
+
"eval_samples_per_second": 502.251,
|
| 92 |
+
"eval_steps_per_second": 62.781,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.56,
|
| 97 |
+
"learning_rate": 4.066666666666667e-05,
|
| 98 |
+
"loss": 7.7924,
|
| 99 |
+
"step": 70
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.56,
|
| 103 |
+
"eval_loss": 7.419986724853516,
|
| 104 |
+
"eval_runtime": 1.9753,
|
| 105 |
+
"eval_samples_per_second": 506.241,
|
| 106 |
+
"eval_steps_per_second": 63.28,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.64,
|
| 111 |
+
"learning_rate": 3.933333333333333e-05,
|
| 112 |
+
"loss": 7.5139,
|
| 113 |
+
"step": 80
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.64,
|
| 117 |
+
"eval_loss": 7.188984394073486,
|
| 118 |
+
"eval_runtime": 1.9721,
|
| 119 |
+
"eval_samples_per_second": 507.08,
|
| 120 |
+
"eval_steps_per_second": 63.385,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.72,
|
| 125 |
+
"learning_rate": 3.8e-05,
|
| 126 |
+
"loss": 7.3932,
|
| 127 |
+
"step": 90
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.72,
|
| 131 |
+
"eval_loss": 7.042924880981445,
|
| 132 |
+
"eval_runtime": 2.0739,
|
| 133 |
+
"eval_samples_per_second": 482.185,
|
| 134 |
+
"eval_steps_per_second": 60.273,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.8,
|
| 139 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 140 |
+
"loss": 7.334,
|
| 141 |
+
"step": 100
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.8,
|
| 145 |
+
"eval_loss": 6.937138557434082,
|
| 146 |
+
"eval_runtime": 2.0003,
|
| 147 |
+
"eval_samples_per_second": 499.914,
|
| 148 |
+
"eval_steps_per_second": 62.489,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.88,
|
| 153 |
+
"learning_rate": 3.5333333333333336e-05,
|
| 154 |
+
"loss": 7.1699,
|
| 155 |
+
"step": 110
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.88,
|
| 159 |
+
"eval_loss": 6.849837779998779,
|
| 160 |
+
"eval_runtime": 2.0147,
|
| 161 |
+
"eval_samples_per_second": 496.356,
|
| 162 |
+
"eval_steps_per_second": 62.045,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.96,
|
| 167 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 168 |
+
"loss": 7.2476,
|
| 169 |
+
"step": 120
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.96,
|
| 173 |
+
"eval_loss": 6.779170036315918,
|
| 174 |
+
"eval_runtime": 2.0584,
|
| 175 |
+
"eval_samples_per_second": 485.82,
|
| 176 |
+
"eval_steps_per_second": 60.727,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.04,
|
| 181 |
+
"learning_rate": 3.266666666666667e-05,
|
| 182 |
+
"loss": 6.8774,
|
| 183 |
+
"step": 130
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.04,
|
| 187 |
+
"eval_loss": 6.709743022918701,
|
| 188 |
+
"eval_runtime": 2.4463,
|
| 189 |
+
"eval_samples_per_second": 408.786,
|
| 190 |
+
"eval_steps_per_second": 51.098,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.12,
|
| 195 |
+
"learning_rate": 3.1333333333333334e-05,
|
| 196 |
+
"loss": 6.7219,
|
| 197 |
+
"step": 140
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.12,
|
| 201 |
+
"eval_loss": 6.656557559967041,
|
| 202 |
+
"eval_runtime": 2.0119,
|
| 203 |
+
"eval_samples_per_second": 497.045,
|
| 204 |
+
"eval_steps_per_second": 62.131,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.2,
|
| 209 |
+
"learning_rate": 3e-05,
|
| 210 |
+
"loss": 6.6353,
|
| 211 |
+
"step": 150
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.2,
|
| 215 |
+
"eval_loss": 6.612905502319336,
|
| 216 |
+
"eval_runtime": 2.0567,
|
| 217 |
+
"eval_samples_per_second": 486.217,
|
| 218 |
+
"eval_steps_per_second": 60.777,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.28,
|
| 223 |
+
"learning_rate": 2.8666666666666668e-05,
|
| 224 |
+
"loss": 6.6524,
|
| 225 |
+
"step": 160
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.28,
|
| 229 |
+
"eval_loss": 6.580767631530762,
|
| 230 |
+
"eval_runtime": 1.9849,
|
| 231 |
+
"eval_samples_per_second": 503.794,
|
| 232 |
+
"eval_steps_per_second": 62.974,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.36,
|
| 237 |
+
"learning_rate": 2.733333333333333e-05,
|
| 238 |
+
"loss": 6.484,
|
| 239 |
+
"step": 170
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.36,
|
| 243 |
+
"eval_loss": 6.5504679679870605,
|
| 244 |
+
"eval_runtime": 2.1014,
|
| 245 |
+
"eval_samples_per_second": 475.877,
|
| 246 |
+
"eval_steps_per_second": 59.485,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.44,
|
| 251 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 252 |
+
"loss": 6.5846,
|
| 253 |
+
"step": 180
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.44,
|
| 257 |
+
"eval_loss": 6.531940460205078,
|
| 258 |
+
"eval_runtime": 3.1229,
|
| 259 |
+
"eval_samples_per_second": 320.22,
|
| 260 |
+
"eval_steps_per_second": 40.027,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.52,
|
| 265 |
+
"learning_rate": 2.466666666666667e-05,
|
| 266 |
+
"loss": 6.558,
|
| 267 |
+
"step": 190
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.52,
|
| 271 |
+
"eval_loss": 6.510298728942871,
|
| 272 |
+
"eval_runtime": 1.9686,
|
| 273 |
+
"eval_samples_per_second": 507.978,
|
| 274 |
+
"eval_steps_per_second": 63.497,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.6,
|
| 279 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 280 |
+
"loss": 6.4792,
|
| 281 |
+
"step": 200
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.6,
|
| 285 |
+
"eval_loss": 6.493106365203857,
|
| 286 |
+
"eval_runtime": 1.8922,
|
| 287 |
+
"eval_samples_per_second": 528.475,
|
| 288 |
+
"eval_steps_per_second": 66.059,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.68,
|
| 293 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 294 |
+
"loss": 6.5203,
|
| 295 |
+
"step": 210
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.68,
|
| 299 |
+
"eval_loss": 6.469159126281738,
|
| 300 |
+
"eval_runtime": 2.0323,
|
| 301 |
+
"eval_samples_per_second": 492.062,
|
| 302 |
+
"eval_steps_per_second": 61.508,
|
| 303 |
+
"step": 210
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.76,
|
| 307 |
+
"learning_rate": 2.0666666666666666e-05,
|
| 308 |
+
"loss": 6.6041,
|
| 309 |
+
"step": 220
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.76,
|
| 313 |
+
"eval_loss": 6.450395107269287,
|
| 314 |
+
"eval_runtime": 3.3679,
|
| 315 |
+
"eval_samples_per_second": 296.917,
|
| 316 |
+
"eval_steps_per_second": 37.115,
|
| 317 |
+
"step": 220
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.84,
|
| 321 |
+
"learning_rate": 1.9333333333333333e-05,
|
| 322 |
+
"loss": 6.646,
|
| 323 |
+
"step": 230
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.84,
|
| 327 |
+
"eval_loss": 6.437198638916016,
|
| 328 |
+
"eval_runtime": 2.0292,
|
| 329 |
+
"eval_samples_per_second": 492.807,
|
| 330 |
+
"eval_steps_per_second": 61.601,
|
| 331 |
+
"step": 230
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.92,
|
| 335 |
+
"learning_rate": 1.8e-05,
|
| 336 |
+
"loss": 6.5665,
|
| 337 |
+
"step": 240
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.92,
|
| 341 |
+
"eval_loss": 6.420088768005371,
|
| 342 |
+
"eval_runtime": 2.0424,
|
| 343 |
+
"eval_samples_per_second": 489.62,
|
| 344 |
+
"eval_steps_per_second": 61.202,
|
| 345 |
+
"step": 240
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.0,
|
| 349 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 350 |
+
"loss": 6.6006,
|
| 351 |
+
"step": 250
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.0,
|
| 355 |
+
"eval_loss": 6.402657508850098,
|
| 356 |
+
"eval_runtime": 1.8829,
|
| 357 |
+
"eval_samples_per_second": 531.107,
|
| 358 |
+
"eval_steps_per_second": 66.388,
|
| 359 |
+
"step": 250
|
| 360 |
+
}
|
| 361 |
+
],
|
| 362 |
+
"logging_steps": 10,
|
| 363 |
+
"max_steps": 375,
|
| 364 |
+
"num_train_epochs": 3,
|
| 365 |
+
"save_steps": 10,
|
| 366 |
+
"total_flos": 29623007232000.0,
|
| 367 |
+
"trial_name": null,
|
| 368 |
+
"trial_params": null
|
| 369 |
+
}
|
checkpoint-250/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:343123aa056dacb81bf4aba5d1ee827cb26f5e4dd6a565a320e1d7e0430ea370
|
| 3 |
+
size 4155
|