Training in progress, step 1700, 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:f13991fe3cf9a0d8f912d55eaacf6ed3a2fb9426d500ec4c1551da576765ba85
|
| 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:c7046913d93cbc685049afa6b24b2a9a34dc5990d21d543bf19afd9346edc937
|
| 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 sha256:881c52916d95773133f31350f99bbb7d3ca1951e219bd8978df431bb56ef135c
|
| 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": 13.
|
| 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,
|
|
@@ -3050,6 +3050,24 @@
|
|
| 3050 |
"mean_token_accuracy": 0.6433569133281708,
|
| 3051 |
"num_tokens": 6163365.0,
|
| 3052 |
"step": 1690
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3053 |
}
|
| 3054 |
],
|
| 3055 |
"logging_steps": 5,
|
|
@@ -3069,7 +3087,7 @@
|
|
| 3069 |
"attributes": {}
|
| 3070 |
}
|
| 3071 |
},
|
| 3072 |
-
"total_flos": 3.
|
| 3073 |
"train_batch_size": 4,
|
| 3074 |
"trial_name": null,
|
| 3075 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 13.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1700,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3050 |
"mean_token_accuracy": 0.6433569133281708,
|
| 3051 |
"num_tokens": 6163365.0,
|
| 3052 |
"step": 1690
|
| 3053 |
+
},
|
| 3054 |
+
{
|
| 3055 |
+
"epoch": 13.038461538461538,
|
| 3056 |
+
"grad_norm": 0.0,
|
| 3057 |
+
"learning_rate": 4.1530000000000004e-05,
|
| 3058 |
+
"loss": 1.7762,
|
| 3059 |
+
"mean_token_accuracy": 0.6436060070991516,
|
| 3060 |
+
"num_tokens": 6181008.0,
|
| 3061 |
+
"step": 1695
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 13.076923076923077,
|
| 3065 |
+
"grad_norm": 0.0,
|
| 3066 |
+
"learning_rate": 4.1504999999999996e-05,
|
| 3067 |
+
"loss": 1.8095,
|
| 3068 |
+
"mean_token_accuracy": 0.6394443988800049,
|
| 3069 |
+
"num_tokens": 6198379.0,
|
| 3070 |
+
"step": 1700
|
| 3071 |
}
|
| 3072 |
],
|
| 3073 |
"logging_steps": 5,
|
|
|
|
| 3087 |
"attributes": {}
|
| 3088 |
}
|
| 3089 |
},
|
| 3090 |
+
"total_flos": 3.1397718761570304e+17,
|
| 3091 |
"train_batch_size": 4,
|
| 3092 |
"trial_name": null,
|
| 3093 |
"trial_params": null
|