Training in progress, step 1760, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cbacd3013327aaa74160c72a32b8a1e7ad63d6497f92dde197c79f3b0afb70b
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dfb1036f848475a8db40bf830cd8e0f4660ba913e08ec9812f9637596e351a5
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:426c835022e7436d10ad2af32cbcbfd3765b2819795f89be9e1d35610f78b570
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 13.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -3158,6 +3158,24 @@
|
|
| 3158 |
"mean_token_accuracy": 0.6487911343574524,
|
| 3159 |
"num_tokens": 6380492.0,
|
| 3160 |
"step": 1750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3161 |
}
|
| 3162 |
],
|
| 3163 |
"logging_steps": 5,
|
|
@@ -3177,7 +3195,7 @@
|
|
| 3177 |
"attributes": {}
|
| 3178 |
}
|
| 3179 |
},
|
| 3180 |
-
"total_flos": 3.
|
| 3181 |
"train_batch_size": 4,
|
| 3182 |
"trial_name": null,
|
| 3183 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 13.538461538461538,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1760,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3158 |
"mean_token_accuracy": 0.6487911343574524,
|
| 3159 |
"num_tokens": 6380492.0,
|
| 3160 |
"step": 1750
|
| 3161 |
+
},
|
| 3162 |
+
{
|
| 3163 |
+
"epoch": 13.5,
|
| 3164 |
+
"grad_norm": 0.0,
|
| 3165 |
+
"learning_rate": 4.123e-05,
|
| 3166 |
+
"loss": 1.7241,
|
| 3167 |
+
"mean_token_accuracy": 0.6540584862232208,
|
| 3168 |
+
"num_tokens": 6399116.0,
|
| 3169 |
+
"step": 1755
|
| 3170 |
+
},
|
| 3171 |
+
{
|
| 3172 |
+
"epoch": 13.538461538461538,
|
| 3173 |
+
"grad_norm": 0.0,
|
| 3174 |
+
"learning_rate": 4.1205e-05,
|
| 3175 |
+
"loss": 1.6792,
|
| 3176 |
+
"mean_token_accuracy": 0.6668368667364121,
|
| 3177 |
+
"num_tokens": 6417790.0,
|
| 3178 |
+
"step": 1760
|
| 3179 |
}
|
| 3180 |
],
|
| 3181 |
"logging_steps": 5,
|
|
|
|
| 3195 |
"attributes": {}
|
| 3196 |
}
|
| 3197 |
},
|
| 3198 |
+
"total_flos": 3.251257065897984e+17,
|
| 3199 |
"train_batch_size": 4,
|
| 3200 |
"trial_name": null,
|
| 3201 |
"trial_params": null
|