Training in progress, step 3300, 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 sha256:3fffc5022761a945cca8744d53d7383d32c92abc72dcabea66395b05a5e8bfca
|
| 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:f308cb93464137b4c0adc1d7ea59b7bb670312444e953d6d767de99fb53bab2b
|
| 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 sha256:434b970e7d7c9eb962c3ce44920f23a29e098cca09f37255db09ada386f794c4
|
| 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": 25.
|
| 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,
|
|
@@ -5930,6 +5930,24 @@
|
|
| 5930 |
"mean_token_accuracy": 0.6447003424167633,
|
| 5931 |
"num_tokens": 11998539.0,
|
| 5932 |
"step": 3290
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5933 |
}
|
| 5934 |
],
|
| 5935 |
"logging_steps": 5,
|
|
@@ -5949,7 +5967,7 @@
|
|
| 5949 |
"attributes": {}
|
| 5950 |
}
|
| 5951 |
},
|
| 5952 |
-
"total_flos": 6.
|
| 5953 |
"train_batch_size": 4,
|
| 5954 |
"trial_name": null,
|
| 5955 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 25.384615384615383,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3300,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5930 |
"mean_token_accuracy": 0.6447003424167633,
|
| 5931 |
"num_tokens": 11998539.0,
|
| 5932 |
"step": 3290
|
| 5933 |
+
},
|
| 5934 |
+
{
|
| 5935 |
+
"epoch": 25.346153846153847,
|
| 5936 |
+
"grad_norm": 0.0,
|
| 5937 |
+
"learning_rate": 3.353e-05,
|
| 5938 |
+
"loss": 1.7875,
|
| 5939 |
+
"mean_token_accuracy": 0.6442469358444214,
|
| 5940 |
+
"num_tokens": 12016433.0,
|
| 5941 |
+
"step": 3295
|
| 5942 |
+
},
|
| 5943 |
+
{
|
| 5944 |
+
"epoch": 25.384615384615383,
|
| 5945 |
+
"grad_norm": 0.0,
|
| 5946 |
+
"learning_rate": 3.3505000000000005e-05,
|
| 5947 |
+
"loss": 1.7792,
|
| 5948 |
+
"mean_token_accuracy": 0.6442890495061875,
|
| 5949 |
+
"num_tokens": 12034074.0,
|
| 5950 |
+
"step": 3300
|
| 5951 |
}
|
| 5952 |
],
|
| 5953 |
"logging_steps": 5,
|
|
|
|
| 5967 |
"attributes": {}
|
| 5968 |
}
|
| 5969 |
},
|
| 5970 |
+
"total_flos": 6.097539980353536e+17,
|
| 5971 |
"train_batch_size": 4,
|
| 5972 |
"trial_name": null,
|
| 5973 |
"trial_params": null
|