Training in progress, step 5600, 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 sha256:8a9fd5edda833c2985fc269536153f318694c2b4aa8d8e9f3b81cba75392d02d
|
| 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 sha256:2b2f22101c7041db565eab7f393d4fa189cff6f019e796ff6c45765729109653
|
| 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 sha256:1c85bb8e9afb3b1993d6e1f940365fc9885a97e53bd653716888c07064b2dbe0
|
| 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": 43.
|
| 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,
|
|
@@ -10070,6 +10070,24 @@
|
|
| 10070 |
"mean_token_accuracy": 0.6442039728164672,
|
| 10071 |
"num_tokens": 20386515.0,
|
| 10072 |
"step": 5590
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10073 |
}
|
| 10074 |
],
|
| 10075 |
"logging_steps": 5,
|
|
@@ -10089,7 +10107,7 @@
|
|
| 10089 |
"attributes": {}
|
| 10090 |
}
|
| 10091 |
},
|
| 10092 |
-
"total_flos": 1.
|
| 10093 |
"train_batch_size": 4,
|
| 10094 |
"trial_name": null,
|
| 10095 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 43.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5600,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10070 |
"mean_token_accuracy": 0.6442039728164672,
|
| 10071 |
"num_tokens": 20386515.0,
|
| 10072 |
"step": 5590
|
| 10073 |
+
},
|
| 10074 |
+
{
|
| 10075 |
+
"epoch": 43.03846153846154,
|
| 10076 |
+
"grad_norm": 0.0,
|
| 10077 |
+
"learning_rate": 2.203e-05,
|
| 10078 |
+
"loss": 1.7707,
|
| 10079 |
+
"mean_token_accuracy": 0.6441226691007614,
|
| 10080 |
+
"num_tokens": 20404313.0,
|
| 10081 |
+
"step": 5595
|
| 10082 |
+
},
|
| 10083 |
+
{
|
| 10084 |
+
"epoch": 43.07692307692308,
|
| 10085 |
+
"grad_norm": 0.0,
|
| 10086 |
+
"learning_rate": 2.2005e-05,
|
| 10087 |
+
"loss": 1.7275,
|
| 10088 |
+
"mean_token_accuracy": 0.6514497637748718,
|
| 10089 |
+
"num_tokens": 20422886.0,
|
| 10090 |
+
"step": 5600
|
| 10091 |
}
|
| 10092 |
],
|
| 10093 |
"logging_steps": 5,
|
|
|
|
| 10107 |
"attributes": {}
|
| 10108 |
}
|
| 10109 |
},
|
| 10110 |
+
"total_flos": 1.0348750002275942e+18,
|
| 10111 |
"train_batch_size": 4,
|
| 10112 |
"trial_name": null,
|
| 10113 |
"trial_params": null
|