Training in progress, step 2200, 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 sha256:4302755f6e21cf7ea750e3266e66350b076ce99ea076300e8cfa1d88c1456163
|
| 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 sha256:7bc51a5c541bbc3aee4c87e4138582998d4403ba4ab2f86fe5a47244b5edd0a7
|
| 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:aa7cc94192cd5522e452a14acc193b1fe5b7538f626239bb03a7cb987e271cce
|
| 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": 16.
|
| 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,
|
|
@@ -3950,6 +3950,24 @@
|
|
| 3950 |
"mean_token_accuracy": 0.6475545018911362,
|
| 3951 |
"num_tokens": 7987748.0,
|
| 3952 |
"step": 2190
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3953 |
}
|
| 3954 |
],
|
| 3955 |
"logging_steps": 5,
|
|
@@ -3969,7 +3987,7 @@
|
|
| 3969 |
"attributes": {}
|
| 3970 |
}
|
| 3971 |
},
|
| 3972 |
-
"total_flos": 4.
|
| 3973 |
"train_batch_size": 4,
|
| 3974 |
"trial_name": null,
|
| 3975 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 16.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3950 |
"mean_token_accuracy": 0.6475545018911362,
|
| 3951 |
"num_tokens": 7987748.0,
|
| 3952 |
"step": 2190
|
| 3953 |
+
},
|
| 3954 |
+
{
|
| 3955 |
+
"epoch": 16.884615384615383,
|
| 3956 |
+
"grad_norm": 0.0,
|
| 3957 |
+
"learning_rate": 3.903e-05,
|
| 3958 |
+
"loss": 1.7839,
|
| 3959 |
+
"mean_token_accuracy": 0.639941617846489,
|
| 3960 |
+
"num_tokens": 8005598.0,
|
| 3961 |
+
"step": 2195
|
| 3962 |
+
},
|
| 3963 |
+
{
|
| 3964 |
+
"epoch": 16.923076923076923,
|
| 3965 |
+
"grad_norm": 0.0,
|
| 3966 |
+
"learning_rate": 3.9005000000000003e-05,
|
| 3967 |
+
"loss": 1.7498,
|
| 3968 |
+
"mean_token_accuracy": 0.6494361340999604,
|
| 3969 |
+
"num_tokens": 8023661.0,
|
| 3970 |
+
"step": 2200
|
| 3971 |
}
|
| 3972 |
],
|
| 3973 |
"logging_steps": 5,
|
|
|
|
| 3987 |
"attributes": {}
|
| 3988 |
}
|
| 3989 |
},
|
| 3990 |
+
"total_flos": 4.065330451002163e+17,
|
| 3991 |
"train_batch_size": 4,
|
| 3992 |
"trial_name": null,
|
| 3993 |
"trial_params": null
|