Training in progress, step 6140, 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 sha256:7c7bffe5d535fd68953aeda61600971620d8c3af5ebcf225c293452c421e43de
|
| 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:fd74ec4680780b79f717796997ffeef20266a0478bbb27f591647963749fbf39
|
| 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 sha256:065e600434220bb26c2aea4e92763be9a047b264b68a326422e21a7ca107c397
|
| 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": 47.
|
| 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,
|
|
@@ -11042,6 +11042,24 @@
|
|
| 11042 |
"mean_token_accuracy": 0.6448232650756835,
|
| 11043 |
"num_tokens": 22357250.0,
|
| 11044 |
"step": 6130
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11045 |
}
|
| 11046 |
],
|
| 11047 |
"logging_steps": 5,
|
|
@@ -11061,7 +11079,7 @@
|
|
| 11061 |
"attributes": {}
|
| 11062 |
}
|
| 11063 |
},
|
| 11064 |
-
"total_flos": 1.
|
| 11065 |
"train_batch_size": 4,
|
| 11066 |
"trial_name": null,
|
| 11067 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 47.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6140,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11042 |
"mean_token_accuracy": 0.6448232650756835,
|
| 11043 |
"num_tokens": 22357250.0,
|
| 11044 |
"step": 6130
|
| 11045 |
+
},
|
| 11046 |
+
{
|
| 11047 |
+
"epoch": 47.19230769230769,
|
| 11048 |
+
"grad_norm": 0.0,
|
| 11049 |
+
"learning_rate": 1.933e-05,
|
| 11050 |
+
"loss": 1.7201,
|
| 11051 |
+
"mean_token_accuracy": 0.6556304097175598,
|
| 11052 |
+
"num_tokens": 22375225.0,
|
| 11053 |
+
"step": 6135
|
| 11054 |
+
},
|
| 11055 |
+
{
|
| 11056 |
+
"epoch": 47.23076923076923,
|
| 11057 |
+
"grad_norm": 0.0,
|
| 11058 |
+
"learning_rate": 1.9305000000000002e-05,
|
| 11059 |
+
"loss": 1.6685,
|
| 11060 |
+
"mean_token_accuracy": 0.6670328795909881,
|
| 11061 |
+
"num_tokens": 22394135.0,
|
| 11062 |
+
"step": 6140
|
| 11063 |
}
|
| 11064 |
],
|
| 11065 |
"logging_steps": 5,
|
|
|
|
| 11079 |
"attributes": {}
|
| 11080 |
}
|
| 11081 |
},
|
| 11082 |
+
"total_flos": 1.1350012886256845e+18,
|
| 11083 |
"train_batch_size": 4,
|
| 11084 |
"trial_name": null,
|
| 11085 |
"trial_params": null
|