Training in progress, step 5560, 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 sha256:785514669d2278cce7681576e35ecdc42e540071d06e597d85674177bbe3faee
|
| 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 sha256:2500c7de8423d23cf262004d51557f40c7ec373cb22f0cb13844fae3cafb01b4
|
| 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 sha256:4d2271bfb005d87ff88a06fb620ffc742848c4fbe0ec16615b4860fe128cf001
|
| 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": 42.
|
| 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,
|
|
@@ -9998,6 +9998,24 @@
|
|
| 9998 |
"mean_token_accuracy": 0.6489108324050903,
|
| 9999 |
"num_tokens": 20241135.0,
|
| 10000 |
"step": 5550
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10001 |
}
|
| 10002 |
],
|
| 10003 |
"logging_steps": 5,
|
|
@@ -10017,7 +10035,7 @@
|
|
| 10017 |
"attributes": {}
|
| 10018 |
}
|
| 10019 |
},
|
| 10020 |
-
"total_flos": 1.
|
| 10021 |
"train_batch_size": 4,
|
| 10022 |
"trial_name": null,
|
| 10023 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 42.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5560,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9998 |
"mean_token_accuracy": 0.6489108324050903,
|
| 9999 |
"num_tokens": 20241135.0,
|
| 10000 |
"step": 5550
|
| 10001 |
+
},
|
| 10002 |
+
{
|
| 10003 |
+
"epoch": 42.73076923076923,
|
| 10004 |
+
"grad_norm": 0.0,
|
| 10005 |
+
"learning_rate": 2.2230000000000002e-05,
|
| 10006 |
+
"loss": 1.722,
|
| 10007 |
+
"mean_token_accuracy": 0.6489439159631729,
|
| 10008 |
+
"num_tokens": 20260178.0,
|
| 10009 |
+
"step": 5555
|
| 10010 |
+
},
|
| 10011 |
+
{
|
| 10012 |
+
"epoch": 42.76923076923077,
|
| 10013 |
+
"grad_norm": 0.0,
|
| 10014 |
+
"learning_rate": 2.2205000000000002e-05,
|
| 10015 |
+
"loss": 1.7384,
|
| 10016 |
+
"mean_token_accuracy": 0.6486925899982452,
|
| 10017 |
+
"num_tokens": 20278793.0,
|
| 10018 |
+
"step": 5560
|
| 10019 |
}
|
| 10020 |
],
|
| 10021 |
"logging_steps": 5,
|
|
|
|
| 10035 |
"attributes": {}
|
| 10036 |
}
|
| 10037 |
},
|
| 10038 |
+
"total_flos": 1.0277051690999808e+18,
|
| 10039 |
"train_batch_size": 4,
|
| 10040 |
"trial_name": null,
|
| 10041 |
"trial_params": null
|