Training in progress, step 2840, 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 sha256:5457586950798d5d6a6ec4490f7bc36d3082899d757f7789793a3ea5dd1263be
|
| 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 sha256:2526bdd581f0b66c4525505c66fd425992ee6eaa9ad0cfe0ef049197a44c1230
|
| 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 sha256:0f258ef28cc869665337f45fe794d5b3ffa81eaab3d60a991cbe2894858c3cd9
|
| 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,
|
|
@@ -5102,6 +5102,24 @@
|
|
| 5102 |
"mean_token_accuracy": 0.6636721462011337,
|
| 5103 |
"num_tokens": 10321523.0,
|
| 5104 |
"step": 2830
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5105 |
}
|
| 5106 |
],
|
| 5107 |
"logging_steps": 5,
|
|
@@ -5121,7 +5139,7 @@
|
|
| 5121 |
"attributes": {}
|
| 5122 |
}
|
| 5123 |
},
|
| 5124 |
-
"total_flos": 5.
|
| 5125 |
"train_batch_size": 4,
|
| 5126 |
"trial_name": null,
|
| 5127 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 21.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2840,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5102 |
"mean_token_accuracy": 0.6636721462011337,
|
| 5103 |
"num_tokens": 10321523.0,
|
| 5104 |
"step": 2830
|
| 5105 |
+
},
|
| 5106 |
+
{
|
| 5107 |
+
"epoch": 21.807692307692307,
|
| 5108 |
+
"grad_norm": 0.0,
|
| 5109 |
+
"learning_rate": 3.583e-05,
|
| 5110 |
+
"loss": 1.7523,
|
| 5111 |
+
"mean_token_accuracy": 0.6470031648874283,
|
| 5112 |
+
"num_tokens": 10339297.0,
|
| 5113 |
+
"step": 2835
|
| 5114 |
+
},
|
| 5115 |
+
{
|
| 5116 |
+
"epoch": 21.846153846153847,
|
| 5117 |
+
"grad_norm": 0.0,
|
| 5118 |
+
"learning_rate": 3.5805e-05,
|
| 5119 |
+
"loss": 1.7419,
|
| 5120 |
+
"mean_token_accuracy": 0.6513529509305954,
|
| 5121 |
+
"num_tokens": 10357839.0,
|
| 5122 |
+
"step": 2840
|
| 5123 |
}
|
| 5124 |
],
|
| 5125 |
"logging_steps": 5,
|
|
|
|
| 5139 |
"attributes": {}
|
| 5140 |
}
|
| 5141 |
},
|
| 5142 |
+
"total_flos": 5.2491099635859456e+17,
|
| 5143 |
"train_batch_size": 4,
|
| 5144 |
"trial_name": null,
|
| 5145 |
"trial_params": null
|