Training in progress, step 530, 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 sha256:13257d887b19bc9e1227e04ef3496b5a8c1375d73fdc296da90574824e013d5d
|
| 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:f3ef86aaf87ad4813c7a60e1f86ca2818d07a502c96740ff3362db427b2077db
|
| 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 sha256:9bbd2f1bbf68171a4d6a560466ad77045b9186a08dc513df98fdc49ccbf2dd8b
|
| 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": 4.
|
| 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,
|
|
@@ -944,6 +944,24 @@
|
|
| 944 |
"mean_token_accuracy": 0.6410065919160843,
|
| 945 |
"num_tokens": 1896420.0,
|
| 946 |
"step": 520
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 947 |
}
|
| 948 |
],
|
| 949 |
"logging_steps": 5,
|
|
@@ -963,7 +981,7 @@
|
|
| 963 |
"attributes": {}
|
| 964 |
}
|
| 965 |
},
|
| 966 |
-
"total_flos": 9.
|
| 967 |
"train_batch_size": 4,
|
| 968 |
"trial_name": null,
|
| 969 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 530,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 944 |
"mean_token_accuracy": 0.6410065919160843,
|
| 945 |
"num_tokens": 1896420.0,
|
| 946 |
"step": 520
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 4.038461538461538,
|
| 950 |
+
"grad_norm": 0.0,
|
| 951 |
+
"learning_rate": 4.7380000000000004e-05,
|
| 952 |
+
"loss": 1.7327,
|
| 953 |
+
"mean_token_accuracy": 0.651974669098854,
|
| 954 |
+
"num_tokens": 1915163.0,
|
| 955 |
+
"step": 525
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 4.076923076923077,
|
| 959 |
+
"grad_norm": 0.0,
|
| 960 |
+
"learning_rate": 4.7355e-05,
|
| 961 |
+
"loss": 1.8077,
|
| 962 |
+
"mean_token_accuracy": 0.6375770300626755,
|
| 963 |
+
"num_tokens": 1932820.0,
|
| 964 |
+
"step": 530
|
| 965 |
}
|
| 966 |
],
|
| 967 |
"logging_steps": 5,
|
|
|
|
| 981 |
"attributes": {}
|
| 982 |
}
|
| 983 |
},
|
| 984 |
+
"total_flos": 9.785050689503232e+16,
|
| 985 |
"train_batch_size": 4,
|
| 986 |
"trial_name": null,
|
| 987 |
"trial_params": null
|