Training in progress, step 500, checkpoint
Browse files- checkpoint-500/config.json +40 -0
- checkpoint-500/generation_config.json +12 -0
- checkpoint-500/model.safetensors +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/trainer_state.json +383 -0
- checkpoint-500/training_args.bin +3 -0
checkpoint-500/config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 128000,
|
| 9 |
+
"eos_token_id": [
|
| 10 |
+
128001,
|
| 11 |
+
128008,
|
| 12 |
+
128009
|
| 13 |
+
],
|
| 14 |
+
"head_dim": 64,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 2048,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 8192,
|
| 19 |
+
"max_position_embeddings": 131072,
|
| 20 |
+
"mlp_bias": false,
|
| 21 |
+
"model_type": "llama",
|
| 22 |
+
"num_attention_heads": 32,
|
| 23 |
+
"num_hidden_layers": 16,
|
| 24 |
+
"num_key_value_heads": 8,
|
| 25 |
+
"pretraining_tp": 1,
|
| 26 |
+
"rms_norm_eps": 1e-05,
|
| 27 |
+
"rope_scaling": {
|
| 28 |
+
"factor": 32.0,
|
| 29 |
+
"high_freq_factor": 4.0,
|
| 30 |
+
"low_freq_factor": 1.0,
|
| 31 |
+
"original_max_position_embeddings": 8192,
|
| 32 |
+
"rope_type": "llama3"
|
| 33 |
+
},
|
| 34 |
+
"rope_theta": 500000.0,
|
| 35 |
+
"tie_word_embeddings": true,
|
| 36 |
+
"torch_dtype": "bfloat16",
|
| 37 |
+
"transformers_version": "4.46.3",
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 128256
|
| 40 |
+
}
|
checkpoint-500/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128008,
|
| 7 |
+
128009
|
| 8 |
+
],
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_p": 0.9,
|
| 11 |
+
"transformers_version": "4.46.3"
|
| 12 |
+
}
|
checkpoint-500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7bb3ad1738e116032ea42588842243587d733cf434eddbb0a80d566d41197a6c
|
| 3 |
+
size 2471645608
|
checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c2bbd9e15fd5fb2ec48ee3e01e36657bf7371667830e01130bdb7123b4f9538
|
| 3 |
+
size 3724602
|
checkpoint-500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc3eea0be68d6bc55683bb3c5f59641cf59c5495cb2cb19696129b9acd61a5dc
|
| 3 |
+
size 14244
|
checkpoint-500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31f20d3fd8f2ca072c88294e1b245d2fc0feec4c84032b4ae4d3711181320962
|
| 3 |
+
size 1064
|
checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,383 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.616088947024199,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.052321778940483975,
|
| 13 |
+
"grad_norm": 73.5,
|
| 14 |
+
"learning_rate": 8.000000000000001e-07,
|
| 15 |
+
"loss": 0.4785,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.10464355788096795,
|
| 20 |
+
"grad_norm": 280.0,
|
| 21 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 22 |
+
"loss": 0.4749,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.15696533682145192,
|
| 27 |
+
"grad_norm": 664.0,
|
| 28 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 29 |
+
"loss": 0.5162,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2092871157619359,
|
| 34 |
+
"grad_norm": 684.0,
|
| 35 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 36 |
+
"loss": 0.7172,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2616088947024199,
|
| 41 |
+
"grad_norm": 209.0,
|
| 42 |
+
"learning_rate": 4.000000000000001e-06,
|
| 43 |
+
"loss": 0.8219,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.31393067364290383,
|
| 48 |
+
"grad_norm": 122.0,
|
| 49 |
+
"learning_rate": 4.800000000000001e-06,
|
| 50 |
+
"loss": 1.1019,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.36625245258338784,
|
| 55 |
+
"grad_norm": 149.0,
|
| 56 |
+
"learning_rate": 5.600000000000001e-06,
|
| 57 |
+
"loss": 1.145,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4185742315238718,
|
| 62 |
+
"grad_norm": 123.5,
|
| 63 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 64 |
+
"loss": 1.1876,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.4708960104643558,
|
| 69 |
+
"grad_norm": 89.0,
|
| 70 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 71 |
+
"loss": 1.207,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5232177894048398,
|
| 76 |
+
"grad_norm": 372.0,
|
| 77 |
+
"learning_rate": 8.000000000000001e-06,
|
| 78 |
+
"loss": 1.0986,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5755395683453237,
|
| 83 |
+
"grad_norm": 69.0,
|
| 84 |
+
"learning_rate": 8.8e-06,
|
| 85 |
+
"loss": 0.8367,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6278613472858077,
|
| 90 |
+
"grad_norm": 60.25,
|
| 91 |
+
"learning_rate": 9.600000000000001e-06,
|
| 92 |
+
"loss": 0.8822,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.6801831262262917,
|
| 97 |
+
"grad_norm": 44.75,
|
| 98 |
+
"learning_rate": 1.04e-05,
|
| 99 |
+
"loss": 1.2104,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7325049051667757,
|
| 104 |
+
"grad_norm": 49.0,
|
| 105 |
+
"learning_rate": 1.1200000000000001e-05,
|
| 106 |
+
"loss": 0.8587,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.7848266841072596,
|
| 111 |
+
"grad_norm": 42.5,
|
| 112 |
+
"learning_rate": 1.2e-05,
|
| 113 |
+
"loss": 0.761,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.8371484630477436,
|
| 118 |
+
"grad_norm": 42.5,
|
| 119 |
+
"learning_rate": 1.2800000000000001e-05,
|
| 120 |
+
"loss": 0.7207,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.8894702419882276,
|
| 125 |
+
"grad_norm": 28.25,
|
| 126 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 127 |
+
"loss": 0.7541,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.9417920209287116,
|
| 132 |
+
"grad_norm": 40.75,
|
| 133 |
+
"learning_rate": 1.4400000000000001e-05,
|
| 134 |
+
"loss": 0.7367,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.9941137998691956,
|
| 139 |
+
"grad_norm": 231.0,
|
| 140 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 141 |
+
"loss": 0.8107,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.0464355788096795,
|
| 146 |
+
"grad_norm": 70.0,
|
| 147 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 148 |
+
"loss": 0.7498,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.0987573577501635,
|
| 153 |
+
"grad_norm": 33.5,
|
| 154 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 155 |
+
"loss": 0.7138,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.1510791366906474,
|
| 160 |
+
"grad_norm": 34.75,
|
| 161 |
+
"learning_rate": 1.76e-05,
|
| 162 |
+
"loss": 0.6399,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.2034009156311314,
|
| 167 |
+
"grad_norm": 20.125,
|
| 168 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 169 |
+
"loss": 0.5844,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.2557226945716153,
|
| 174 |
+
"grad_norm": 34.25,
|
| 175 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 176 |
+
"loss": 0.6765,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.3080444735120995,
|
| 181 |
+
"grad_norm": 37.0,
|
| 182 |
+
"learning_rate": 2e-05,
|
| 183 |
+
"loss": 3.7542,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.3603662524525835,
|
| 188 |
+
"grad_norm": 27.25,
|
| 189 |
+
"learning_rate": 1.9999025240093045e-05,
|
| 190 |
+
"loss": 0.7183,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.4126880313930674,
|
| 195 |
+
"grad_norm": 20.25,
|
| 196 |
+
"learning_rate": 1.9996101150403543e-05,
|
| 197 |
+
"loss": 0.5714,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.4650098103335514,
|
| 202 |
+
"grad_norm": 21.125,
|
| 203 |
+
"learning_rate": 1.9991228300988586e-05,
|
| 204 |
+
"loss": 0.5506,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.5173315892740353,
|
| 209 |
+
"grad_norm": 23.625,
|
| 210 |
+
"learning_rate": 1.9984407641819812e-05,
|
| 211 |
+
"loss": 0.5253,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.5696533682145193,
|
| 216 |
+
"grad_norm": 20.75,
|
| 217 |
+
"learning_rate": 1.9975640502598243e-05,
|
| 218 |
+
"loss": 0.5671,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.6219751471550032,
|
| 223 |
+
"grad_norm": 15.6875,
|
| 224 |
+
"learning_rate": 1.9964928592495046e-05,
|
| 225 |
+
"loss": 0.4991,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.6742969260954872,
|
| 230 |
+
"grad_norm": 18.125,
|
| 231 |
+
"learning_rate": 1.9952273999818312e-05,
|
| 232 |
+
"loss": 0.5376,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.7266187050359711,
|
| 237 |
+
"grad_norm": 18.125,
|
| 238 |
+
"learning_rate": 1.9937679191605964e-05,
|
| 239 |
+
"loss": 0.5307,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.7789404839764553,
|
| 244 |
+
"grad_norm": 17.125,
|
| 245 |
+
"learning_rate": 1.9921147013144782e-05,
|
| 246 |
+
"loss": 0.522,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.831262262916939,
|
| 251 |
+
"grad_norm": 11.375,
|
| 252 |
+
"learning_rate": 1.9902680687415704e-05,
|
| 253 |
+
"loss": 0.4873,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.8835840418574232,
|
| 258 |
+
"grad_norm": 19.625,
|
| 259 |
+
"learning_rate": 1.988228381446553e-05,
|
| 260 |
+
"loss": 0.4609,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.9359058207979072,
|
| 265 |
+
"grad_norm": 15.0625,
|
| 266 |
+
"learning_rate": 1.985996037070505e-05,
|
| 267 |
+
"loss": 0.4225,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.9882275997383911,
|
| 272 |
+
"grad_norm": 19.0,
|
| 273 |
+
"learning_rate": 1.983571470813386e-05,
|
| 274 |
+
"loss": 0.4309,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.040549378678875,
|
| 279 |
+
"grad_norm": 18.5,
|
| 280 |
+
"learning_rate": 1.9809551553491918e-05,
|
| 281 |
+
"loss": 0.4062,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.092871157619359,
|
| 286 |
+
"grad_norm": 10.25,
|
| 287 |
+
"learning_rate": 1.9781476007338058e-05,
|
| 288 |
+
"loss": 0.3827,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.145192936559843,
|
| 293 |
+
"grad_norm": 23.75,
|
| 294 |
+
"learning_rate": 1.9751493543055634e-05,
|
| 295 |
+
"loss": 0.3883,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.197514715500327,
|
| 300 |
+
"grad_norm": 14.8125,
|
| 301 |
+
"learning_rate": 1.9719610005785466e-05,
|
| 302 |
+
"loss": 0.4069,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.249836494440811,
|
| 307 |
+
"grad_norm": 23.125,
|
| 308 |
+
"learning_rate": 1.9685831611286312e-05,
|
| 309 |
+
"loss": 0.3815,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 2.302158273381295,
|
| 314 |
+
"grad_norm": 10.8125,
|
| 315 |
+
"learning_rate": 1.9650164944723116e-05,
|
| 316 |
+
"loss": 0.3719,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.354480052321779,
|
| 321 |
+
"grad_norm": 15.6875,
|
| 322 |
+
"learning_rate": 1.961261695938319e-05,
|
| 323 |
+
"loss": 0.4038,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.4068018312622628,
|
| 328 |
+
"grad_norm": 18.875,
|
| 329 |
+
"learning_rate": 1.9573194975320672e-05,
|
| 330 |
+
"loss": 0.3864,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.459123610202747,
|
| 335 |
+
"grad_norm": 21.375,
|
| 336 |
+
"learning_rate": 1.9531906677929472e-05,
|
| 337 |
+
"loss": 0.3941,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.5114453891432307,
|
| 342 |
+
"grad_norm": 24.75,
|
| 343 |
+
"learning_rate": 1.9488760116444966e-05,
|
| 344 |
+
"loss": 0.3661,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.563767168083715,
|
| 349 |
+
"grad_norm": 30.0,
|
| 350 |
+
"learning_rate": 1.944376370237481e-05,
|
| 351 |
+
"loss": 0.3604,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.616088947024199,
|
| 356 |
+
"grad_norm": 11.6875,
|
| 357 |
+
"learning_rate": 1.9396926207859085e-05,
|
| 358 |
+
"loss": 0.3618,
|
| 359 |
+
"step": 500
|
| 360 |
+
}
|
| 361 |
+
],
|
| 362 |
+
"logging_steps": 10,
|
| 363 |
+
"max_steps": 2500,
|
| 364 |
+
"num_input_tokens_seen": 0,
|
| 365 |
+
"num_train_epochs": 14,
|
| 366 |
+
"save_steps": 500,
|
| 367 |
+
"stateful_callbacks": {
|
| 368 |
+
"TrainerControl": {
|
| 369 |
+
"args": {
|
| 370 |
+
"should_epoch_stop": false,
|
| 371 |
+
"should_evaluate": false,
|
| 372 |
+
"should_log": false,
|
| 373 |
+
"should_save": true,
|
| 374 |
+
"should_training_stop": false
|
| 375 |
+
},
|
| 376 |
+
"attributes": {}
|
| 377 |
+
}
|
| 378 |
+
},
|
| 379 |
+
"total_flos": 1.9128047871039898e+17,
|
| 380 |
+
"train_batch_size": 4,
|
| 381 |
+
"trial_name": null,
|
| 382 |
+
"trial_params": null
|
| 383 |
+
}
|
checkpoint-500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e10f4c3493d7c03a6772e09fa67dd6af5fe700f25044f5df7816afc8f4ab8195
|
| 3 |
+
size 5432
|