Training in progress, step 9420, 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 sha256:8885d25f382e38937046230d8a051bd0d3198548cf8e09431675a057b06ff400
|
| 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 sha256:9f168e04a4e5409bbf7b691d26cb4c3f0116fabc0c91acdace0c718f57962235
|
| 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 sha256:30aaa336cc9dbe5ea7c7cace9f5d4e9dd290e3851af353b90786c2a48f93ae7f
|
| 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": 72.
|
| 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,
|
|
@@ -16946,6 +16946,24 @@
|
|
| 16946 |
"mean_token_accuracy": 0.6518394500017166,
|
| 16947 |
"num_tokens": 34319958.0,
|
| 16948 |
"step": 9410
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16949 |
}
|
| 16950 |
],
|
| 16951 |
"logging_steps": 5,
|
|
@@ -16965,7 +16983,7 @@
|
|
| 16965 |
"attributes": {}
|
| 16966 |
}
|
| 16967 |
},
|
| 16968 |
-
"total_flos": 1.
|
| 16969 |
"train_batch_size": 4,
|
| 16970 |
"trial_name": null,
|
| 16971 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 72.46153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9420,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16946 |
"mean_token_accuracy": 0.6518394500017166,
|
| 16947 |
"num_tokens": 34319958.0,
|
| 16948 |
"step": 9410
|
| 16949 |
+
},
|
| 16950 |
+
{
|
| 16951 |
+
"epoch": 72.42307692307692,
|
| 16952 |
+
"grad_norm": 0.0,
|
| 16953 |
+
"learning_rate": 2.93e-06,
|
| 16954 |
+
"loss": 1.7295,
|
| 16955 |
+
"mean_token_accuracy": 0.6590041428804397,
|
| 16956 |
+
"num_tokens": 34338437.0,
|
| 16957 |
+
"step": 9415
|
| 16958 |
+
},
|
| 16959 |
+
{
|
| 16960 |
+
"epoch": 72.46153846153847,
|
| 16961 |
+
"grad_norm": 0.0,
|
| 16962 |
+
"learning_rate": 2.905e-06,
|
| 16963 |
+
"loss": 1.8063,
|
| 16964 |
+
"mean_token_accuracy": 0.6363181412220001,
|
| 16965 |
+
"num_tokens": 34356326.0,
|
| 16966 |
+
"step": 9420
|
| 16967 |
}
|
| 16968 |
],
|
| 16969 |
"logging_steps": 5,
|
|
|
|
| 16983 |
"attributes": {}
|
| 16984 |
}
|
| 16985 |
},
|
| 16986 |
+
"total_flos": 1.7422183134624154e+18,
|
| 16987 |
"train_batch_size": 4,
|
| 16988 |
"trial_name": null,
|
| 16989 |
"trial_params": null
|