Commit
•
e7e5fc7
1
Parent(s):
291954c
End of training
Browse files- README.md +3 -2
- all_results.json +12 -0
- eval_results.json +7 -0
- runs/Dec29_10-14-45_64-181-222-101/events.out.tfevents.1735491903.64-181-222-101.39025.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +414 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: llama3
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: sft_full
|
|
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# sft_full
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 1.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: sft_full
|
|
|
|
| 16 |
|
| 17 |
# sft_full
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the healthcaremagic dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.7460
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9850746268656714,
|
| 3 |
+
"eval_loss": 1.7460383176803589,
|
| 4 |
+
"eval_runtime": 306.5437,
|
| 5 |
+
"eval_samples_per_second": 32.622,
|
| 6 |
+
"eval_steps_per_second": 0.512,
|
| 7 |
+
"total_flos": 165772559646720.0,
|
| 8 |
+
"train_loss": 1.5532971572875978,
|
| 9 |
+
"train_runtime": 24046.0291,
|
| 10 |
+
"train_samples_per_second": 11.228,
|
| 11 |
+
"train_steps_per_second": 0.022
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9850746268656714,
|
| 3 |
+
"eval_loss": 1.7460383176803589,
|
| 4 |
+
"eval_runtime": 306.5437,
|
| 5 |
+
"eval_samples_per_second": 32.622,
|
| 6 |
+
"eval_steps_per_second": 0.512
|
| 7 |
+
}
|
runs/Dec29_10-14-45_64-181-222-101/events.out.tfevents.1735491903.64-181-222-101.39025.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df6db43cebbf07e3e4b28f82cfae48f4bfdeeb46d460edb428bb219e100de631
|
| 3 |
+
size 359
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9850746268656714,
|
| 3 |
+
"total_flos": 165772559646720.0,
|
| 4 |
+
"train_loss": 1.5532971572875978,
|
| 5 |
+
"train_runtime": 24046.0291,
|
| 6 |
+
"train_samples_per_second": 11.228,
|
| 7 |
+
"train_steps_per_second": 0.022
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,414 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9850746268656714,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 525,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05685856432125089,
|
| 13 |
+
"grad_norm": 5.9803857599927595,
|
| 14 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 15 |
+
"loss": 3.0422,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.11371712864250177,
|
| 20 |
+
"grad_norm": 2.217843129478048,
|
| 21 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 22 |
+
"loss": 2.4412,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.17057569296375266,
|
| 27 |
+
"grad_norm": 1.8496604433568333,
|
| 28 |
+
"learning_rate": 9.99910461334869e-06,
|
| 29 |
+
"loss": 2.1975,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.22743425728500355,
|
| 34 |
+
"grad_norm": 2.211490671202065,
|
| 35 |
+
"learning_rate": 9.983195548029173e-06,
|
| 36 |
+
"loss": 2.0619,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.28429282160625446,
|
| 41 |
+
"grad_norm": 1.4387489754724267,
|
| 42 |
+
"learning_rate": 9.947461858764978e-06,
|
| 43 |
+
"loss": 1.9967,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3411513859275053,
|
| 48 |
+
"grad_norm": 1.8279329868726204,
|
| 49 |
+
"learning_rate": 9.892045704727864e-06,
|
| 50 |
+
"loss": 1.9387,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.39800995024875624,
|
| 55 |
+
"grad_norm": 1.6474902291327627,
|
| 56 |
+
"learning_rate": 9.817167547748729e-06,
|
| 57 |
+
"loss": 1.9172,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4548685145700071,
|
| 62 |
+
"grad_norm": 1.657541170060607,
|
| 63 |
+
"learning_rate": 9.723125275255325e-06,
|
| 64 |
+
"loss": 1.8705,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.511727078891258,
|
| 69 |
+
"grad_norm": 1.696974285018719,
|
| 70 |
+
"learning_rate": 9.610293015188067e-06,
|
| 71 |
+
"loss": 1.8323,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5685856432125089,
|
| 76 |
+
"grad_norm": 1.5303782561090193,
|
| 77 |
+
"learning_rate": 9.47911964760858e-06,
|
| 78 |
+
"loss": 1.8171,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.6254442075337597,
|
| 83 |
+
"grad_norm": 1.5651172480757691,
|
| 84 |
+
"learning_rate": 9.330127018922195e-06,
|
| 85 |
+
"loss": 1.8148,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6823027718550106,
|
| 90 |
+
"grad_norm": 1.5409210855141433,
|
| 91 |
+
"learning_rate": 9.163907865818806e-06,
|
| 92 |
+
"loss": 1.783,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.7391613361762616,
|
| 97 |
+
"grad_norm": 1.5363163924078007,
|
| 98 |
+
"learning_rate": 8.98112345719122e-06,
|
| 99 |
+
"loss": 1.7854,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7960199004975125,
|
| 104 |
+
"grad_norm": 1.5576565905261832,
|
| 105 |
+
"learning_rate": 8.782500963412156e-06,
|
| 106 |
+
"loss": 1.7504,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.8528784648187633,
|
| 111 |
+
"grad_norm": 1.521719538010432,
|
| 112 |
+
"learning_rate": 8.568830563435695e-06,
|
| 113 |
+
"loss": 1.7504,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.9097370291400142,
|
| 118 |
+
"grad_norm": 1.5810495823530497,
|
| 119 |
+
"learning_rate": 8.34096230123198e-06,
|
| 120 |
+
"loss": 1.7645,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.9665955934612651,
|
| 125 |
+
"grad_norm": 1.41921208948242,
|
| 126 |
+
"learning_rate": 8.099802704061194e-06,
|
| 127 |
+
"loss": 1.7222,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.023454157782516,
|
| 132 |
+
"grad_norm": 2.303489781396609,
|
| 133 |
+
"learning_rate": 7.846311176040331e-06,
|
| 134 |
+
"loss": 1.6839,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.080312722103767,
|
| 139 |
+
"grad_norm": 1.7804848302086473,
|
| 140 |
+
"learning_rate": 7.581496181350203e-06,
|
| 141 |
+
"loss": 1.5172,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.1371712864250179,
|
| 146 |
+
"grad_norm": 1.5922077446873317,
|
| 147 |
+
"learning_rate": 7.30641123226703e-06,
|
| 148 |
+
"loss": 1.5129,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.1940298507462686,
|
| 153 |
+
"grad_norm": 1.600712736103309,
|
| 154 |
+
"learning_rate": 7.022150697979385e-06,
|
| 155 |
+
"loss": 1.5027,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.2508884150675195,
|
| 160 |
+
"grad_norm": 1.5405911558473169,
|
| 161 |
+
"learning_rate": 6.7298454508642945e-06,
|
| 162 |
+
"loss": 1.4733,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.3077469793887704,
|
| 167 |
+
"grad_norm": 1.6005186629850159,
|
| 168 |
+
"learning_rate": 6.4306583675428435e-06,
|
| 169 |
+
"loss": 1.5009,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.3646055437100213,
|
| 174 |
+
"grad_norm": 1.6179249599606138,
|
| 175 |
+
"learning_rate": 6.125779702613471e-06,
|
| 176 |
+
"loss": 1.4981,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.4214641080312722,
|
| 181 |
+
"grad_norm": 1.5595473213575002,
|
| 182 |
+
"learning_rate": 5.816422353467562e-06,
|
| 183 |
+
"loss": 1.4929,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.4783226723525231,
|
| 188 |
+
"grad_norm": 1.610680010605817,
|
| 189 |
+
"learning_rate": 5.503817035025341e-06,
|
| 190 |
+
"loss": 1.4962,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.535181236673774,
|
| 195 |
+
"grad_norm": 1.5401109765819234,
|
| 196 |
+
"learning_rate": 5.189207383588353e-06,
|
| 197 |
+
"loss": 1.4828,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.5920398009950247,
|
| 202 |
+
"grad_norm": 1.5437992683845965,
|
| 203 |
+
"learning_rate": 4.873845009286879e-06,
|
| 204 |
+
"loss": 1.4943,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.6488983653162759,
|
| 209 |
+
"grad_norm": 1.569798351736018,
|
| 210 |
+
"learning_rate": 4.5589845168051176e-06,
|
| 211 |
+
"loss": 1.47,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.7057569296375266,
|
| 216 |
+
"grad_norm": 1.5635972598860413,
|
| 217 |
+
"learning_rate": 4.245878514193131e-06,
|
| 218 |
+
"loss": 1.4717,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.7626154939587777,
|
| 223 |
+
"grad_norm": 1.583256520765993,
|
| 224 |
+
"learning_rate": 3.935772629621996e-06,
|
| 225 |
+
"loss": 1.4759,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.8194740582800284,
|
| 230 |
+
"grad_norm": 1.5703071827809085,
|
| 231 |
+
"learning_rate": 3.62990055590697e-06,
|
| 232 |
+
"loss": 1.4731,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.8763326226012793,
|
| 237 |
+
"grad_norm": 1.5673344510472709,
|
| 238 |
+
"learning_rate": 3.3294791425130512e-06,
|
| 239 |
+
"loss": 1.4609,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.9331911869225302,
|
| 244 |
+
"grad_norm": 1.5649245970464676,
|
| 245 |
+
"learning_rate": 3.035703554568331e-06,
|
| 246 |
+
"loss": 1.4557,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.9900497512437811,
|
| 251 |
+
"grad_norm": 1.5535579680886489,
|
| 252 |
+
"learning_rate": 2.749742518144061e-06,
|
| 253 |
+
"loss": 1.4604,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.046908315565032,
|
| 258 |
+
"grad_norm": 2.6898081511100944,
|
| 259 |
+
"learning_rate": 2.4727336707170973e-06,
|
| 260 |
+
"loss": 1.2976,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.1037668798862827,
|
| 265 |
+
"grad_norm": 2.294462090007101,
|
| 266 |
+
"learning_rate": 2.2057790353119533e-06,
|
| 267 |
+
"loss": 1.2109,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 2.160625444207534,
|
| 272 |
+
"grad_norm": 2.0734336172332375,
|
| 273 |
+
"learning_rate": 1.949940636327671e-06,
|
| 274 |
+
"loss": 1.2101,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.2174840085287846,
|
| 279 |
+
"grad_norm": 1.9313522409801105,
|
| 280 |
+
"learning_rate": 1.7062362744910321e-06,
|
| 281 |
+
"loss": 1.2124,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.2743425728500357,
|
| 286 |
+
"grad_norm": 1.9741447028673955,
|
| 287 |
+
"learning_rate": 1.4756354777446004e-06,
|
| 288 |
+
"loss": 1.2204,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.3312011371712864,
|
| 293 |
+
"grad_norm": 1.9826092702551152,
|
| 294 |
+
"learning_rate": 1.2590556441781725e-06,
|
| 295 |
+
"loss": 1.2031,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.388059701492537,
|
| 300 |
+
"grad_norm": 1.9337513040949874,
|
| 301 |
+
"learning_rate": 1.057358392348171e-06,
|
| 302 |
+
"loss": 1.1978,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.4449182658137882,
|
| 307 |
+
"grad_norm": 1.9619207022209448,
|
| 308 |
+
"learning_rate": 8.713461335044981e-07,
|
| 309 |
+
"loss": 1.1929,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 2.501776830135039,
|
| 314 |
+
"grad_norm": 1.9462643434600588,
|
| 315 |
+
"learning_rate": 7.017588793615499e-07,
|
| 316 |
+
"loss": 1.2075,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.55863539445629,
|
| 321 |
+
"grad_norm": 1.9622874707007205,
|
| 322 |
+
"learning_rate": 5.492712981130171e-07,
|
| 323 |
+
"loss": 1.2068,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.6154939587775408,
|
| 328 |
+
"grad_norm": 1.9185457493104283,
|
| 329 |
+
"learning_rate": 4.144900304025101e-07,
|
| 330 |
+
"loss": 1.1924,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.672352523098792,
|
| 335 |
+
"grad_norm": 1.9287168348109207,
|
| 336 |
+
"learning_rate": 2.979512759278719e-07,
|
| 337 |
+
"loss": 1.1847,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.7292110874200426,
|
| 342 |
+
"grad_norm": 1.898626201871725,
|
| 343 |
+
"learning_rate": 2.0011866028038617e-07,
|
| 344 |
+
"loss": 1.192,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.7860696517412933,
|
| 349 |
+
"grad_norm": 1.9641608263451322,
|
| 350 |
+
"learning_rate": 1.2138139050522024e-07,
|
| 351 |
+
"loss": 1.204,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.8429282160625444,
|
| 356 |
+
"grad_norm": 1.9152149742726723,
|
| 357 |
+
"learning_rate": 6.20527067208232e-08,
|
| 358 |
+
"loss": 1.2093,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.8429282160625444,
|
| 363 |
+
"eval_loss": 1.7461528778076172,
|
| 364 |
+
"eval_runtime": 307.7688,
|
| 365 |
+
"eval_samples_per_second": 32.492,
|
| 366 |
+
"eval_steps_per_second": 0.51,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 2.8997867803837956,
|
| 371 |
+
"grad_norm": 1.9127782775890796,
|
| 372 |
+
"learning_rate": 2.236863595720562e-08,
|
| 373 |
+
"loss": 1.1844,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.9566453447050463,
|
| 378 |
+
"grad_norm": 1.8938021124768716,
|
| 379 |
+
"learning_rate": 2.4870531706872037e-09,
|
| 380 |
+
"loss": 1.1984,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.9850746268656714,
|
| 385 |
+
"step": 525,
|
| 386 |
+
"total_flos": 165772559646720.0,
|
| 387 |
+
"train_loss": 1.5532971572875978,
|
| 388 |
+
"train_runtime": 24046.0291,
|
| 389 |
+
"train_samples_per_second": 11.228,
|
| 390 |
+
"train_steps_per_second": 0.022
|
| 391 |
+
}
|
| 392 |
+
],
|
| 393 |
+
"logging_steps": 10,
|
| 394 |
+
"max_steps": 525,
|
| 395 |
+
"num_input_tokens_seen": 0,
|
| 396 |
+
"num_train_epochs": 3,
|
| 397 |
+
"save_steps": 500,
|
| 398 |
+
"stateful_callbacks": {
|
| 399 |
+
"TrainerControl": {
|
| 400 |
+
"args": {
|
| 401 |
+
"should_epoch_stop": false,
|
| 402 |
+
"should_evaluate": false,
|
| 403 |
+
"should_log": false,
|
| 404 |
+
"should_save": true,
|
| 405 |
+
"should_training_stop": true
|
| 406 |
+
},
|
| 407 |
+
"attributes": {}
|
| 408 |
+
}
|
| 409 |
+
},
|
| 410 |
+
"total_flos": 165772559646720.0,
|
| 411 |
+
"train_batch_size": 8,
|
| 412 |
+
"trial_name": null,
|
| 413 |
+
"trial_params": null
|
| 414 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|