Training in progress, step 7270, 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:aa28e1a4288e012954a82f6f3545ff3c70d65dd62f1dfce244b5d5e023d32101
|
| 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 sha256:3265c04dfe1ff14d94013cc65020b74fc5c38e864f2eaa6d5124d57985938c4c
|
| 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:a7e0c4ec89fa268a0885bb2ee64470b80bac672b73adc610b17a221a90a6102f
|
| 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": 55.
|
| 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,
|
|
@@ -13076,6 +13076,24 @@
|
|
| 13076 |
"mean_token_accuracy": 0.6436378836631775,
|
| 13077 |
"num_tokens": 26477032.0,
|
| 13078 |
"step": 7260
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13079 |
}
|
| 13080 |
],
|
| 13081 |
"logging_steps": 5,
|
|
@@ -13095,7 +13113,7 @@
|
|
| 13095 |
"attributes": {}
|
| 13096 |
}
|
| 13097 |
},
|
| 13098 |
-
"total_flos": 1.
|
| 13099 |
"train_batch_size": 4,
|
| 13100 |
"trial_name": null,
|
| 13101 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 55.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7270,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13076 |
"mean_token_accuracy": 0.6436378836631775,
|
| 13077 |
"num_tokens": 26477032.0,
|
| 13078 |
"step": 7260
|
| 13079 |
+
},
|
| 13080 |
+
{
|
| 13081 |
+
"epoch": 55.88461538461539,
|
| 13082 |
+
"grad_norm": 0.0,
|
| 13083 |
+
"learning_rate": 1.3680000000000001e-05,
|
| 13084 |
+
"loss": 1.7543,
|
| 13085 |
+
"mean_token_accuracy": 0.6499706447124481,
|
| 13086 |
+
"num_tokens": 26495861.0,
|
| 13087 |
+
"step": 7265
|
| 13088 |
+
},
|
| 13089 |
+
{
|
| 13090 |
+
"epoch": 55.92307692307692,
|
| 13091 |
+
"grad_norm": 0.0,
|
| 13092 |
+
"learning_rate": 1.3655e-05,
|
| 13093 |
+
"loss": 1.714,
|
| 13094 |
+
"mean_token_accuracy": 0.6544960319995881,
|
| 13095 |
+
"num_tokens": 26514486.0,
|
| 13096 |
+
"step": 7270
|
| 13097 |
}
|
| 13098 |
],
|
| 13099 |
"logging_steps": 5,
|
|
|
|
| 13113 |
"attributes": {}
|
| 13114 |
}
|
| 13115 |
},
|
| 13116 |
+
"total_flos": 1.3443563563175117e+18,
|
| 13117 |
"train_batch_size": 4,
|
| 13118 |
"trial_name": null,
|
| 13119 |
"trial_params": null
|