Training in progress, step 1640, 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 sha256:5c180991de62837b70b4caf482216f6dbd23fd2dcebca10f96c6176374d8864c
|
| 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 sha256:24bfaa6c36f85f05ce01653706e072302df8de7dc8b32a08a509056e430f3fd6
|
| 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 sha256:5ed1d4d6422fc88537add5b01c0bcbaaca62ed7c52aa4b0108dd69c8e5c24536
|
| 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": 12.
|
| 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,
|
|
@@ -2942,6 +2942,24 @@
|
|
| 2942 |
"mean_token_accuracy": 0.6752032458782196,
|
| 2943 |
"num_tokens": 5944267.0,
|
| 2944 |
"step": 1630
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2945 |
}
|
| 2946 |
],
|
| 2947 |
"logging_steps": 5,
|
|
@@ -2961,7 +2979,7 @@
|
|
| 2961 |
"attributes": {}
|
| 2962 |
}
|
| 2963 |
},
|
| 2964 |
-
"total_flos": 3.
|
| 2965 |
"train_batch_size": 4,
|
| 2966 |
"trial_name": null,
|
| 2967 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 12.615384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1640,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2942 |
"mean_token_accuracy": 0.6752032458782196,
|
| 2943 |
"num_tokens": 5944267.0,
|
| 2944 |
"step": 1630
|
| 2945 |
+
},
|
| 2946 |
+
{
|
| 2947 |
+
"epoch": 12.576923076923077,
|
| 2948 |
+
"grad_norm": 0.0,
|
| 2949 |
+
"learning_rate": 4.1830000000000004e-05,
|
| 2950 |
+
"loss": 1.7544,
|
| 2951 |
+
"mean_token_accuracy": 0.6387367337942124,
|
| 2952 |
+
"num_tokens": 5962881.0,
|
| 2953 |
+
"step": 1635
|
| 2954 |
+
},
|
| 2955 |
+
{
|
| 2956 |
+
"epoch": 12.615384615384615,
|
| 2957 |
+
"grad_norm": 0.0,
|
| 2958 |
+
"learning_rate": 4.1805e-05,
|
| 2959 |
+
"loss": 1.7518,
|
| 2960 |
+
"mean_token_accuracy": 0.6540467470884324,
|
| 2961 |
+
"num_tokens": 5980352.0,
|
| 2962 |
+
"step": 1640
|
| 2963 |
}
|
| 2964 |
],
|
| 2965 |
"logging_steps": 5,
|
|
|
|
| 2979 |
"attributes": {}
|
| 2980 |
}
|
| 2981 |
},
|
| 2982 |
+
"total_flos": 3.028818596555981e+17,
|
| 2983 |
"train_batch_size": 4,
|
| 2984 |
"trial_name": null,
|
| 2985 |
"trial_params": null
|