Training in progress, step 3320, 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 sha256:9c476dc54657bd47ebb5ee4f12ea91c29f3c4954935697df21e3b850827afd15
|
| 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:f619e6bcea01bc2672da9e2c4fa7e45cc93021a1f777f5daf338020a6a376981
|
| 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:ec39b48359d3709f2632813f7d46dd7df9a440d9e6645f42b7fe83810b59db16
|
| 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": 25.
|
| 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,
|
|
@@ -5966,6 +5966,24 @@
|
|
| 5966 |
"mean_token_accuracy": 0.632660773396492,
|
| 5967 |
"num_tokens": 12068538.0,
|
| 5968 |
"step": 3310
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5969 |
}
|
| 5970 |
],
|
| 5971 |
"logging_steps": 5,
|
|
@@ -5985,7 +6003,7 @@
|
|
| 5985 |
"attributes": {}
|
| 5986 |
}
|
| 5987 |
},
|
| 5988 |
-
"total_flos": 6.
|
| 5989 |
"train_batch_size": 4,
|
| 5990 |
"trial_name": null,
|
| 5991 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 25.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3320,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5966 |
"mean_token_accuracy": 0.632660773396492,
|
| 5967 |
"num_tokens": 12068538.0,
|
| 5968 |
"step": 3310
|
| 5969 |
+
},
|
| 5970 |
+
{
|
| 5971 |
+
"epoch": 25.5,
|
| 5972 |
+
"grad_norm": 0.0,
|
| 5973 |
+
"learning_rate": 3.3430000000000003e-05,
|
| 5974 |
+
"loss": 1.6571,
|
| 5975 |
+
"mean_token_accuracy": 0.6714397668838501,
|
| 5976 |
+
"num_tokens": 12087276.0,
|
| 5977 |
+
"step": 3315
|
| 5978 |
+
},
|
| 5979 |
+
{
|
| 5980 |
+
"epoch": 25.53846153846154,
|
| 5981 |
+
"grad_norm": 0.0,
|
| 5982 |
+
"learning_rate": 3.3405e-05,
|
| 5983 |
+
"loss": 1.7512,
|
| 5984 |
+
"mean_token_accuracy": 0.6499413967132568,
|
| 5985 |
+
"num_tokens": 12105620.0,
|
| 5986 |
+
"step": 3320
|
| 5987 |
}
|
| 5988 |
],
|
| 5989 |
"logging_steps": 5,
|
|
|
|
| 6003 |
"attributes": {}
|
| 6004 |
}
|
| 6005 |
},
|
| 6006 |
+
"total_flos": 6.133362143536742e+17,
|
| 6007 |
"train_batch_size": 4,
|
| 6008 |
"trial_name": null,
|
| 6009 |
"trial_params": null
|