Training in progress, step 7280, 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 sha256:54dc5db5612afcfb07dc16243adbc023b0670938d31b488d9e339b37400f8ea7
|
| 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 sha256:8901d8198a5e7d9ab1dd6270efe30b888f9432022eb3b963df26f55788a686d3
|
| 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 sha256:6d93b8fe04dd5c1e14a793e6d7f68add17d752137957cf2672e3b17e63a6a7b0
|
| 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":
|
| 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,
|
|
@@ -13094,6 +13094,24 @@
|
|
| 13094 |
"mean_token_accuracy": 0.6544960319995881,
|
| 13095 |
"num_tokens": 26514486.0,
|
| 13096 |
"step": 7270
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13097 |
}
|
| 13098 |
],
|
| 13099 |
"logging_steps": 5,
|
|
@@ -13113,7 +13131,7 @@
|
|
| 13113 |
"attributes": {}
|
| 13114 |
}
|
| 13115 |
},
|
| 13116 |
-
"total_flos": 1.
|
| 13117 |
"train_batch_size": 4,
|
| 13118 |
"trial_name": null,
|
| 13119 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 56.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7280,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13094 |
"mean_token_accuracy": 0.6544960319995881,
|
| 13095 |
"num_tokens": 26514486.0,
|
| 13096 |
"step": 7270
|
| 13097 |
+
},
|
| 13098 |
+
{
|
| 13099 |
+
"epoch": 55.96153846153846,
|
| 13100 |
+
"grad_norm": 0.0,
|
| 13101 |
+
"learning_rate": 1.3630000000000002e-05,
|
| 13102 |
+
"loss": 1.7599,
|
| 13103 |
+
"mean_token_accuracy": 0.6501589000225068,
|
| 13104 |
+
"num_tokens": 26532126.0,
|
| 13105 |
+
"step": 7275
|
| 13106 |
+
},
|
| 13107 |
+
{
|
| 13108 |
+
"epoch": 56.0,
|
| 13109 |
+
"grad_norm": 0.0,
|
| 13110 |
+
"learning_rate": 1.3605000000000001e-05,
|
| 13111 |
+
"loss": 1.7521,
|
| 13112 |
+
"mean_token_accuracy": 0.6498360931873322,
|
| 13113 |
+
"num_tokens": 26549880.0,
|
| 13114 |
+
"step": 7280
|
| 13115 |
}
|
| 13116 |
],
|
| 13117 |
"logging_steps": 5,
|
|
|
|
| 13131 |
"attributes": {}
|
| 13132 |
}
|
| 13133 |
},
|
| 13134 |
+
"total_flos": 1.3461413514795418e+18,
|
| 13135 |
"train_batch_size": 4,
|
| 13136 |
"trial_name": null,
|
| 13137 |
"trial_params": null
|