Training in progress, step 540, 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 sha256:3980bcaa5569025efec49bf19c0793bafe668f1d5934360279d8ed2ac480e37c
|
| 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 sha256:9dc9313c5747cf7c17e842f07adfb0f7c6d60449896c42c65abcd95ceb8d66da
|
| 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:c0c174a0077e626d42d8d1581de99efe4151b89d5d79a61fe898a6f87c3a9a43
|
| 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": 4.
|
| 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,
|
|
@@ -962,6 +962,24 @@
|
|
| 962 |
"mean_token_accuracy": 0.6375770300626755,
|
| 963 |
"num_tokens": 1932820.0,
|
| 964 |
"step": 530
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 965 |
}
|
| 966 |
],
|
| 967 |
"logging_steps": 5,
|
|
@@ -981,7 +999,7 @@
|
|
| 981 |
"attributes": {}
|
| 982 |
}
|
| 983 |
},
|
| 984 |
-
"total_flos": 9.
|
| 985 |
"train_batch_size": 4,
|
| 986 |
"trial_name": null,
|
| 987 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.153846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 540,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 962 |
"mean_token_accuracy": 0.6375770300626755,
|
| 963 |
"num_tokens": 1932820.0,
|
| 964 |
"step": 530
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 4.115384615384615,
|
| 968 |
+
"grad_norm": 0.0,
|
| 969 |
+
"learning_rate": 4.733e-05,
|
| 970 |
+
"loss": 1.7939,
|
| 971 |
+
"mean_token_accuracy": 0.635331529378891,
|
| 972 |
+
"num_tokens": 1951154.0,
|
| 973 |
+
"step": 535
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 4.153846153846154,
|
| 977 |
+
"grad_norm": 0.0,
|
| 978 |
+
"learning_rate": 4.7305e-05,
|
| 979 |
+
"loss": 1.7697,
|
| 980 |
+
"mean_token_accuracy": 0.6442851930856704,
|
| 981 |
+
"num_tokens": 1968989.0,
|
| 982 |
+
"step": 540
|
| 983 |
}
|
| 984 |
],
|
| 985 |
"logging_steps": 5,
|
|
|
|
| 999 |
"attributes": {}
|
| 1000 |
}
|
| 1001 |
},
|
| 1002 |
+
"total_flos": 9.972346570407936e+16,
|
| 1003 |
"train_batch_size": 4,
|
| 1004 |
"trial_name": null,
|
| 1005 |
"trial_params": null
|