Training in progress, step 3410, 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:e908eb6a0d3a58f7466ecf51e1808216bb5977c2726892093155d64a4255d9a9
|
| 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:ef930b983f37b2c20a44f53c62d21fa9fe85b8caaa05f096b43dc6388b8ed6a4
|
| 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 sha256:90c533cc75b5003ea8d44ee6abd97a36c04c19ffe93ec8748324157f54d464f0
|
| 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": 26.
|
| 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,
|
|
@@ -6128,6 +6128,24 @@
|
|
| 6128 |
"mean_token_accuracy": 0.6502564907073974,
|
| 6129 |
"num_tokens": 12399802.0,
|
| 6130 |
"step": 3400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6131 |
}
|
| 6132 |
],
|
| 6133 |
"logging_steps": 5,
|
|
@@ -6147,7 +6165,7 @@
|
|
| 6147 |
"attributes": {}
|
| 6148 |
}
|
| 6149 |
},
|
| 6150 |
-
"total_flos": 6.
|
| 6151 |
"train_batch_size": 4,
|
| 6152 |
"trial_name": null,
|
| 6153 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 26.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3410,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6128 |
"mean_token_accuracy": 0.6502564907073974,
|
| 6129 |
"num_tokens": 12399802.0,
|
| 6130 |
"step": 3400
|
| 6131 |
+
},
|
| 6132 |
+
{
|
| 6133 |
+
"epoch": 26.192307692307693,
|
| 6134 |
+
"grad_norm": 0.0,
|
| 6135 |
+
"learning_rate": 3.298e-05,
|
| 6136 |
+
"loss": 1.7704,
|
| 6137 |
+
"mean_token_accuracy": 0.6401029378175735,
|
| 6138 |
+
"num_tokens": 12417656.0,
|
| 6139 |
+
"step": 3405
|
| 6140 |
+
},
|
| 6141 |
+
{
|
| 6142 |
+
"epoch": 26.23076923076923,
|
| 6143 |
+
"grad_norm": 0.0,
|
| 6144 |
+
"learning_rate": 3.2955000000000006e-05,
|
| 6145 |
+
"loss": 1.6876,
|
| 6146 |
+
"mean_token_accuracy": 0.6598240792751312,
|
| 6147 |
+
"num_tokens": 12436367.0,
|
| 6148 |
+
"step": 3410
|
| 6149 |
}
|
| 6150 |
],
|
| 6151 |
"logging_steps": 5,
|
|
|
|
| 6165 |
"attributes": {}
|
| 6166 |
}
|
| 6167 |
},
|
| 6168 |
+
"total_flos": 6.300774111957811e+17,
|
| 6169 |
"train_batch_size": 4,
|
| 6170 |
"trial_name": null,
|
| 6171 |
"trial_params": null
|