Training in progress, step 2760, 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 sha256:68cddbb2d37442337f130545fcf4b9ae37b0a1d340d921a0e125ba58dba966c4
|
| 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:a39bd00a2a6b927cb72ff5ccd8536de60749f6aadf1436dfee6a96e9f575459d
|
| 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 sha256:6464394786eaa367ae738bbd89346f1f8e347deacda6a184a011b92c22d2713c
|
| 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": 21.
|
| 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,
|
|
@@ -4958,6 +4958,24 @@
|
|
| 4958 |
"mean_token_accuracy": 0.6536423653364182,
|
| 4959 |
"num_tokens": 10027897.0,
|
| 4960 |
"step": 2750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4961 |
}
|
| 4962 |
],
|
| 4963 |
"logging_steps": 5,
|
|
@@ -4977,7 +4995,7 @@
|
|
| 4977 |
"attributes": {}
|
| 4978 |
}
|
| 4979 |
},
|
| 4980 |
-
"total_flos": 5.
|
| 4981 |
"train_batch_size": 4,
|
| 4982 |
"trial_name": null,
|
| 4983 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 21.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2760,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4958 |
"mean_token_accuracy": 0.6536423653364182,
|
| 4959 |
"num_tokens": 10027897.0,
|
| 4960 |
"step": 2750
|
| 4961 |
+
},
|
| 4962 |
+
{
|
| 4963 |
+
"epoch": 21.192307692307693,
|
| 4964 |
+
"grad_norm": 0.0,
|
| 4965 |
+
"learning_rate": 3.6230000000000004e-05,
|
| 4966 |
+
"loss": 1.7402,
|
| 4967 |
+
"mean_token_accuracy": 0.6494254291057586,
|
| 4968 |
+
"num_tokens": 10046965.0,
|
| 4969 |
+
"step": 2755
|
| 4970 |
+
},
|
| 4971 |
+
{
|
| 4972 |
+
"epoch": 21.23076923076923,
|
| 4973 |
+
"grad_norm": 0.0,
|
| 4974 |
+
"learning_rate": 3.6205e-05,
|
| 4975 |
+
"loss": 1.758,
|
| 4976 |
+
"mean_token_accuracy": 0.6502227276563645,
|
| 4977 |
+
"num_tokens": 10065041.0,
|
| 4978 |
+
"step": 2760
|
| 4979 |
}
|
| 4980 |
],
|
| 4981 |
"logging_steps": 5,
|
|
|
|
| 4995 |
"attributes": {}
|
| 4996 |
}
|
| 4997 |
},
|
| 4998 |
+
"total_flos": 5.09962892414976e+17,
|
| 4999 |
"train_batch_size": 4,
|
| 5000 |
"trial_name": null,
|
| 5001 |
"trial_params": null
|