Training in progress, step 3360, 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 sha256:3fb6cd8da03b8390532b9c43ffb374ad061d5e3f79bd69876afd3361efae758e
|
| 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:df4f180bc9ede643ec29241a5e9fdbfeca953e973d1be5fb25f8f361130f935b
|
| 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:a95c73961c1ade03602a924f08362e1b45fc8a49bead9ece0dffec343083e46e
|
| 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": 25.
|
| 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,
|
|
@@ -6038,6 +6038,24 @@
|
|
| 6038 |
"mean_token_accuracy": 0.6405314236879349,
|
| 6039 |
"num_tokens": 12215896.0,
|
| 6040 |
"step": 3350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6041 |
}
|
| 6042 |
],
|
| 6043 |
"logging_steps": 5,
|
|
@@ -6057,7 +6075,7 @@
|
|
| 6057 |
"attributes": {}
|
| 6058 |
}
|
| 6059 |
},
|
| 6060 |
-
"total_flos": 6.
|
| 6061 |
"train_batch_size": 4,
|
| 6062 |
"trial_name": null,
|
| 6063 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 25.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3360,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6038 |
"mean_token_accuracy": 0.6405314236879349,
|
| 6039 |
"num_tokens": 12215896.0,
|
| 6040 |
"step": 3350
|
| 6041 |
+
},
|
| 6042 |
+
{
|
| 6043 |
+
"epoch": 25.807692307692307,
|
| 6044 |
+
"grad_norm": 0.0,
|
| 6045 |
+
"learning_rate": 3.323e-05,
|
| 6046 |
+
"loss": 1.7424,
|
| 6047 |
+
"mean_token_accuracy": 0.6420567870140076,
|
| 6048 |
+
"num_tokens": 12234723.0,
|
| 6049 |
+
"step": 3355
|
| 6050 |
+
},
|
| 6051 |
+
{
|
| 6052 |
+
"epoch": 25.846153846153847,
|
| 6053 |
+
"grad_norm": 0.0,
|
| 6054 |
+
"learning_rate": 3.3205000000000005e-05,
|
| 6055 |
+
"loss": 1.6715,
|
| 6056 |
+
"mean_token_accuracy": 0.6686410069465637,
|
| 6057 |
+
"num_tokens": 12253662.0,
|
| 6058 |
+
"step": 3360
|
| 6059 |
}
|
| 6060 |
],
|
| 6061 |
"logging_steps": 5,
|
|
|
|
| 6075 |
"attributes": {}
|
| 6076 |
}
|
| 6077 |
},
|
| 6078 |
+
"total_flos": 6.208415458172928e+17,
|
| 6079 |
"train_batch_size": 4,
|
| 6080 |
"trial_name": null,
|
| 6081 |
"trial_params": null
|