Training in progress, step 1650, 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 sha256:1d35bf6df65cb993a6d01147d9a956e2d0ddb9999b75c1b7f7a904bdd2f78619
|
| 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 sha256:3db7a1dd7c6d7ed320aa99a2edb6867c669cf074d7eeff10a33677f376168e00
|
| 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 sha256:3d9867261dee8a87ec1cdf214cf719c022817458bf2c5db8f2d3fa40563bacc8
|
| 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,
|
|
@@ -2960,6 +2960,24 @@
|
|
| 2960 |
"mean_token_accuracy": 0.6540467470884324,
|
| 2961 |
"num_tokens": 5980352.0,
|
| 2962 |
"step": 1640
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2963 |
}
|
| 2964 |
],
|
| 2965 |
"logging_steps": 5,
|
|
@@ -2979,7 +2997,7 @@
|
|
| 2979 |
"attributes": {}
|
| 2980 |
}
|
| 2981 |
},
|
| 2982 |
-
"total_flos": 3.
|
| 2983 |
"train_batch_size": 4,
|
| 2984 |
"trial_name": null,
|
| 2985 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 12.692307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1650,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2960 |
"mean_token_accuracy": 0.6540467470884324,
|
| 2961 |
"num_tokens": 5980352.0,
|
| 2962 |
"step": 1640
|
| 2963 |
+
},
|
| 2964 |
+
{
|
| 2965 |
+
"epoch": 12.653846153846153,
|
| 2966 |
+
"grad_norm": 0.0,
|
| 2967 |
+
"learning_rate": 4.178e-05,
|
| 2968 |
+
"loss": 1.6636,
|
| 2969 |
+
"mean_token_accuracy": 0.6685753583908081,
|
| 2970 |
+
"num_tokens": 5998878.0,
|
| 2971 |
+
"step": 1645
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 12.692307692307692,
|
| 2975 |
+
"grad_norm": 0.0,
|
| 2976 |
+
"learning_rate": 4.1755e-05,
|
| 2977 |
+
"loss": 1.7515,
|
| 2978 |
+
"mean_token_accuracy": 0.6498158782720566,
|
| 2979 |
+
"num_tokens": 6016722.0,
|
| 2980 |
+
"step": 1650
|
| 2981 |
}
|
| 2982 |
],
|
| 2983 |
"logging_steps": 5,
|
|
|
|
| 2997 |
"attributes": {}
|
| 2998 |
}
|
| 2999 |
},
|
| 3000 |
+
"total_flos": 3.0476767957549056e+17,
|
| 3001 |
"train_batch_size": 4,
|
| 3002 |
"trial_name": null,
|
| 3003 |
"trial_params": null
|