Training in progress, step 2770, 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 sha256:19631a8772241bae9b2c95e73d488d27f7921d9ce76e4a8e10e9743baeec8788
|
| 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 sha256:438c779cbce0d2c16f9b29926ae5548a47adef9dbe2d062969a68a17d00580d9
|
| 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 sha256:84b8f655865e11be270db56bc7dfd363d838c3776cf1b0df7ed17dac870490d6
|
| 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": 21.
|
| 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,
|
|
@@ -4976,6 +4976,24 @@
|
|
| 4976 |
"mean_token_accuracy": 0.6502227276563645,
|
| 4977 |
"num_tokens": 10065041.0,
|
| 4978 |
"step": 2760
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4979 |
}
|
| 4980 |
],
|
| 4981 |
"logging_steps": 5,
|
|
@@ -4995,7 +5013,7 @@
|
|
| 4995 |
"attributes": {}
|
| 4996 |
}
|
| 4997 |
},
|
| 4998 |
-
"total_flos": 5.
|
| 4999 |
"train_batch_size": 4,
|
| 5000 |
"trial_name": null,
|
| 5001 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 21.307692307692307,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2770,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4976 |
"mean_token_accuracy": 0.6502227276563645,
|
| 4977 |
"num_tokens": 10065041.0,
|
| 4978 |
"step": 2760
|
| 4979 |
+
},
|
| 4980 |
+
{
|
| 4981 |
+
"epoch": 21.26923076923077,
|
| 4982 |
+
"grad_norm": 0.0,
|
| 4983 |
+
"learning_rate": 3.618e-05,
|
| 4984 |
+
"loss": 1.805,
|
| 4985 |
+
"mean_token_accuracy": 0.6402064859867096,
|
| 4986 |
+
"num_tokens": 10082396.0,
|
| 4987 |
+
"step": 2765
|
| 4988 |
+
},
|
| 4989 |
+
{
|
| 4990 |
+
"epoch": 21.307692307692307,
|
| 4991 |
+
"grad_norm": 0.0,
|
| 4992 |
+
"learning_rate": 3.6155e-05,
|
| 4993 |
+
"loss": 1.7417,
|
| 4994 |
+
"mean_token_accuracy": 0.6509008765220642,
|
| 4995 |
+
"num_tokens": 10100522.0,
|
| 4996 |
+
"step": 2770
|
| 4997 |
}
|
| 4998 |
],
|
| 4999 |
"logging_steps": 5,
|
|
|
|
| 5013 |
"attributes": {}
|
| 5014 |
}
|
| 5015 |
},
|
| 5016 |
+
"total_flos": 5.1182156110086144e+17,
|
| 5017 |
"train_batch_size": 4,
|
| 5018 |
"trial_name": null,
|
| 5019 |
"trial_params": null
|