Training in progress, step 4410, 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 sha256:857fa453f06f9353f43ca1af0997323d87ff7a3cd9498d61374a82653c102b29
|
| 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:e705ffb1c42f664be330f61375e4fc89d92d2395530e28fce989a9f7bf552db0
|
| 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:c5b4c65ec90c61b4edbd267549f2e774abe5f65ea1067eeddec8d9a0d6552120
|
| 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": 33.
|
| 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,
|
|
@@ -7928,6 +7928,24 @@
|
|
| 7928 |
"mean_token_accuracy": 0.6424099951982498,
|
| 7929 |
"num_tokens": 16047811.0,
|
| 7930 |
"step": 4400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7931 |
}
|
| 7932 |
],
|
| 7933 |
"logging_steps": 5,
|
|
@@ -7947,7 +7965,7 @@
|
|
| 7947 |
"attributes": {}
|
| 7948 |
}
|
| 7949 |
},
|
| 7950 |
-
"total_flos": 8.
|
| 7951 |
"train_batch_size": 4,
|
| 7952 |
"trial_name": null,
|
| 7953 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 33.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4410,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7928 |
"mean_token_accuracy": 0.6424099951982498,
|
| 7929 |
"num_tokens": 16047811.0,
|
| 7930 |
"step": 4400
|
| 7931 |
+
},
|
| 7932 |
+
{
|
| 7933 |
+
"epoch": 33.88461538461539,
|
| 7934 |
+
"grad_norm": 0.0,
|
| 7935 |
+
"learning_rate": 2.798e-05,
|
| 7936 |
+
"loss": 1.737,
|
| 7937 |
+
"mean_token_accuracy": 0.6514830589294434,
|
| 7938 |
+
"num_tokens": 16065304.0,
|
| 7939 |
+
"step": 4405
|
| 7940 |
+
},
|
| 7941 |
+
{
|
| 7942 |
+
"epoch": 33.92307692307692,
|
| 7943 |
+
"grad_norm": 0.0,
|
| 7944 |
+
"learning_rate": 2.7955000000000003e-05,
|
| 7945 |
+
"loss": 1.7418,
|
| 7946 |
+
"mean_token_accuracy": 0.652796396613121,
|
| 7947 |
+
"num_tokens": 16083292.0,
|
| 7948 |
+
"step": 4410
|
| 7949 |
}
|
| 7950 |
],
|
| 7951 |
"logging_steps": 5,
|
|
|
|
| 7965 |
"attributes": {}
|
| 7966 |
}
|
| 7967 |
},
|
| 7968 |
+
"total_flos": 8.150714708174438e+17,
|
| 7969 |
"train_batch_size": 4,
|
| 7970 |
"trial_name": null,
|
| 7971 |
"trial_params": null
|