Training in progress, step 5530, 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 sha256:9829ddbe3dd2cfa19e1878b51589265a3f13e0231ac5d1283b58650c56a7e3bb
|
| 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:fcf5a235863e01589abf7b94c70f749ebe98cd3c51ef75fce2b370bfb4e901eb
|
| 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 sha256:3da44a5e37178801218cf0816fb1f5a2f4bbe81f1adac03d61883ee5e2994363
|
| 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": 42.
|
| 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,
|
|
@@ -9944,6 +9944,24 @@
|
|
| 9944 |
"mean_token_accuracy": 0.6478333413600922,
|
| 9945 |
"num_tokens": 20130707.0,
|
| 9946 |
"step": 5520
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9947 |
}
|
| 9948 |
],
|
| 9949 |
"logging_steps": 5,
|
|
@@ -9963,7 +9981,7 @@
|
|
| 9963 |
"attributes": {}
|
| 9964 |
}
|
| 9965 |
},
|
| 9966 |
-
"total_flos": 1.
|
| 9967 |
"train_batch_size": 4,
|
| 9968 |
"trial_name": null,
|
| 9969 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 42.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5530,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9944 |
"mean_token_accuracy": 0.6478333413600922,
|
| 9945 |
"num_tokens": 20130707.0,
|
| 9946 |
"step": 5520
|
| 9947 |
+
},
|
| 9948 |
+
{
|
| 9949 |
+
"epoch": 42.5,
|
| 9950 |
+
"grad_norm": 0.0,
|
| 9951 |
+
"learning_rate": 2.2380000000000003e-05,
|
| 9952 |
+
"loss": 1.7299,
|
| 9953 |
+
"mean_token_accuracy": 0.6528987497091293,
|
| 9954 |
+
"num_tokens": 20149020.0,
|
| 9955 |
+
"step": 5525
|
| 9956 |
+
},
|
| 9957 |
+
{
|
| 9958 |
+
"epoch": 42.53846153846154,
|
| 9959 |
+
"grad_norm": 0.0,
|
| 9960 |
+
"learning_rate": 2.2355000000000002e-05,
|
| 9961 |
+
"loss": 1.7313,
|
| 9962 |
+
"mean_token_accuracy": 0.6519591569900512,
|
| 9963 |
+
"num_tokens": 20167484.0,
|
| 9964 |
+
"step": 5530
|
| 9965 |
}
|
| 9966 |
],
|
| 9967 |
"logging_steps": 5,
|
|
|
|
| 9981 |
"attributes": {}
|
| 9982 |
}
|
| 9983 |
},
|
| 9984 |
+
"total_flos": 1.0219252906185523e+18,
|
| 9985 |
"train_batch_size": 4,
|
| 9986 |
"trial_name": null,
|
| 9987 |
"trial_params": null
|