Training in progress, step 8380, 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 sha256:43dcddca44af527caa5c7e48eb5283dede7bd1891ea6163f61946ba7072ed758
|
| 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 sha256:9a1ebd1e34a7f3a85c779940eb13427f990c400df85612e881b9b591d1833c3b
|
| 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 sha256:8f13fe850fbfb74b2b6d499bc3e245e0227bab5aab84f267fbb671219967855c
|
| 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": 64.
|
| 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,
|
|
@@ -15074,6 +15074,24 @@
|
|
| 15074 |
"mean_token_accuracy": 0.6422168552875519,
|
| 15075 |
"num_tokens": 30526994.0,
|
| 15076 |
"step": 8370
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15077 |
}
|
| 15078 |
],
|
| 15079 |
"logging_steps": 5,
|
|
@@ -15093,7 +15111,7 @@
|
|
| 15093 |
"attributes": {}
|
| 15094 |
}
|
| 15095 |
},
|
| 15096 |
-
"total_flos": 1.
|
| 15097 |
"train_batch_size": 4,
|
| 15098 |
"trial_name": null,
|
| 15099 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 64.46153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8380,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15074 |
"mean_token_accuracy": 0.6422168552875519,
|
| 15075 |
"num_tokens": 30526994.0,
|
| 15076 |
"step": 8370
|
| 15077 |
+
},
|
| 15078 |
+
{
|
| 15079 |
+
"epoch": 64.42307692307692,
|
| 15080 |
+
"grad_norm": 0.0,
|
| 15081 |
+
"learning_rate": 8.13e-06,
|
| 15082 |
+
"loss": 1.7371,
|
| 15083 |
+
"mean_token_accuracy": 0.6487582057714463,
|
| 15084 |
+
"num_tokens": 30545290.0,
|
| 15085 |
+
"step": 8375
|
| 15086 |
+
},
|
| 15087 |
+
{
|
| 15088 |
+
"epoch": 64.46153846153847,
|
| 15089 |
+
"grad_norm": 0.0,
|
| 15090 |
+
"learning_rate": 8.105e-06,
|
| 15091 |
+
"loss": 1.7529,
|
| 15092 |
+
"mean_token_accuracy": 0.649326092004776,
|
| 15093 |
+
"num_tokens": 30563300.0,
|
| 15094 |
+
"step": 8380
|
| 15095 |
}
|
| 15096 |
],
|
| 15097 |
"logging_steps": 5,
|
|
|
|
| 15111 |
"attributes": {}
|
| 15112 |
}
|
| 15113 |
},
|
| 15114 |
+
"total_flos": 1.5496139693614694e+18,
|
| 15115 |
"train_batch_size": 4,
|
| 15116 |
"trial_name": null,
|
| 15117 |
"trial_params": null
|