Training in progress, step 5020, 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 sha256:54548cc1ba5d304c9176bd68739ab917792b47d276e36b831f30c9f24ee84649
|
| 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 sha256:0ab75bc0639127858890325337a95137f4f935317ecb8c945d5e553a2404cf26
|
| 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 sha256:78a74020bd18616c3ec029d43dcb8bc25e349a326d0038bfdba6989b41828a2c
|
| 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": 38.
|
| 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,
|
|
@@ -9026,6 +9026,24 @@
|
|
| 9026 |
"mean_token_accuracy": 0.6435254126787185,
|
| 9027 |
"num_tokens": 18270734.0,
|
| 9028 |
"step": 5010
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9029 |
}
|
| 9030 |
],
|
| 9031 |
"logging_steps": 5,
|
|
@@ -9045,7 +9063,7 @@
|
|
| 9045 |
"attributes": {}
|
| 9046 |
}
|
| 9047 |
},
|
| 9048 |
-
"total_flos": 9.
|
| 9049 |
"train_batch_size": 4,
|
| 9050 |
"trial_name": null,
|
| 9051 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 38.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5020,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9026 |
"mean_token_accuracy": 0.6435254126787185,
|
| 9027 |
"num_tokens": 18270734.0,
|
| 9028 |
"step": 5010
|
| 9029 |
+
},
|
| 9030 |
+
{
|
| 9031 |
+
"epoch": 38.57692307692308,
|
| 9032 |
+
"grad_norm": 0.0,
|
| 9033 |
+
"learning_rate": 2.493e-05,
|
| 9034 |
+
"loss": 1.7659,
|
| 9035 |
+
"mean_token_accuracy": 0.6490629822015762,
|
| 9036 |
+
"num_tokens": 18288300.0,
|
| 9037 |
+
"step": 5015
|
| 9038 |
+
},
|
| 9039 |
+
{
|
| 9040 |
+
"epoch": 38.61538461538461,
|
| 9041 |
+
"grad_norm": 0.0,
|
| 9042 |
+
"learning_rate": 2.4905e-05,
|
| 9043 |
+
"loss": 1.7339,
|
| 9044 |
+
"mean_token_accuracy": 0.6582322597503663,
|
| 9045 |
+
"num_tokens": 18306234.0,
|
| 9046 |
+
"step": 5020
|
| 9047 |
}
|
| 9048 |
],
|
| 9049 |
"logging_steps": 5,
|
|
|
|
| 9063 |
"attributes": {}
|
| 9064 |
}
|
| 9065 |
},
|
| 9066 |
+
"total_flos": 9.277084444852224e+17,
|
| 9067 |
"train_batch_size": 4,
|
| 9068 |
"trial_name": null,
|
| 9069 |
"trial_params": null
|