Training in progress, step 4530, 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:b81edf6734bb53ab37d3c36c62b7ef854de731bd76e50a28dc598466943ce629
|
| 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:dfb58c2a7ff20ed15c1ddd9d729a9cbacdc10e6aeaaa09079370f3a18623e596
|
| 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 sha256:3f13ef08d07b765bae40641f443554d47f19104b9340909943480a9a68362a76
|
| 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": 34.
|
| 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,
|
|
@@ -8144,6 +8144,24 @@
|
|
| 8144 |
"mean_token_accuracy": 0.6530486464500427,
|
| 8145 |
"num_tokens": 16484278.0,
|
| 8146 |
"step": 4520
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8147 |
}
|
| 8148 |
],
|
| 8149 |
"logging_steps": 5,
|
|
@@ -8163,7 +8181,7 @@
|
|
| 8163 |
"attributes": {}
|
| 8164 |
}
|
| 8165 |
},
|
| 8166 |
-
"total_flos": 8.
|
| 8167 |
"train_batch_size": 4,
|
| 8168 |
"trial_name": null,
|
| 8169 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 34.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4530,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8144 |
"mean_token_accuracy": 0.6530486464500427,
|
| 8145 |
"num_tokens": 16484278.0,
|
| 8146 |
"step": 4520
|
| 8147 |
+
},
|
| 8148 |
+
{
|
| 8149 |
+
"epoch": 34.80769230769231,
|
| 8150 |
+
"grad_norm": 0.0,
|
| 8151 |
+
"learning_rate": 2.738e-05,
|
| 8152 |
+
"loss": 1.7237,
|
| 8153 |
+
"mean_token_accuracy": 0.6497306555509568,
|
| 8154 |
+
"num_tokens": 16502702.0,
|
| 8155 |
+
"step": 4525
|
| 8156 |
+
},
|
| 8157 |
+
{
|
| 8158 |
+
"epoch": 34.84615384615385,
|
| 8159 |
+
"grad_norm": 0.0,
|
| 8160 |
+
"learning_rate": 2.7355e-05,
|
| 8161 |
+
"loss": 1.6833,
|
| 8162 |
+
"mean_token_accuracy": 0.6642057120800018,
|
| 8163 |
+
"num_tokens": 16521906.0,
|
| 8164 |
+
"step": 4530
|
| 8165 |
}
|
| 8166 |
],
|
| 8167 |
"logging_steps": 5,
|
|
|
|
| 8181 |
"attributes": {}
|
| 8182 |
}
|
| 8183 |
},
|
| 8184 |
+
"total_flos": 8.373969302328115e+17,
|
| 8185 |
"train_batch_size": 4,
|
| 8186 |
"trial_name": null,
|
| 8187 |
"trial_params": null
|