Training in progress, step 8360, 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:d85f1ff518291aa3d0078bb4485d6be4ca3e36d74edc7bb5f5c42cde6310bb70
|
| 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:ebcbf6d5bae52eb4b9f83be204092660b3a84f676f49b2883bb2763af7fbc13a
|
| 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:bca406ea1ab24e3b886a22b5aba0b05347e12f94bd3c5a7b8ffface8e5d1c3d3
|
| 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,
|
|
@@ -15038,6 +15038,24 @@
|
|
| 15038 |
"mean_token_accuracy": 0.6602605700492858,
|
| 15039 |
"num_tokens": 30453103.0,
|
| 15040 |
"step": 8350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15041 |
}
|
| 15042 |
],
|
| 15043 |
"logging_steps": 5,
|
|
@@ -15057,7 +15075,7 @@
|
|
| 15057 |
"attributes": {}
|
| 15058 |
}
|
| 15059 |
},
|
| 15060 |
-
"total_flos": 1.
|
| 15061 |
"train_batch_size": 4,
|
| 15062 |
"trial_name": null,
|
| 15063 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 64.3076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8360,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15038 |
"mean_token_accuracy": 0.6602605700492858,
|
| 15039 |
"num_tokens": 30453103.0,
|
| 15040 |
"step": 8350
|
| 15041 |
+
},
|
| 15042 |
+
{
|
| 15043 |
+
"epoch": 64.26923076923077,
|
| 15044 |
+
"grad_norm": 0.0,
|
| 15045 |
+
"learning_rate": 8.23e-06,
|
| 15046 |
+
"loss": 1.6849,
|
| 15047 |
+
"mean_token_accuracy": 0.6583765029907227,
|
| 15048 |
+
"num_tokens": 30471800.0,
|
| 15049 |
+
"step": 8355
|
| 15050 |
+
},
|
| 15051 |
+
{
|
| 15052 |
+
"epoch": 64.3076923076923,
|
| 15053 |
+
"grad_norm": 0.0,
|
| 15054 |
+
"learning_rate": 8.205e-06,
|
| 15055 |
+
"loss": 1.7548,
|
| 15056 |
+
"mean_token_accuracy": 0.648283451795578,
|
| 15057 |
+
"num_tokens": 30490316.0,
|
| 15058 |
+
"step": 8360
|
| 15059 |
}
|
| 15060 |
],
|
| 15061 |
"logging_steps": 5,
|
|
|
|
| 15075 |
"attributes": {}
|
| 15076 |
}
|
| 15077 |
},
|
| 15078 |
+
"total_flos": 1.5459612551022182e+18,
|
| 15079 |
"train_batch_size": 4,
|
| 15080 |
"trial_name": null,
|
| 15081 |
"trial_params": null
|