Training in progress, step 1660, 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 sha256:4829719568e423f754af5ad509e4ad39413b40f7db59e7376df183a266e1170f
|
| 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:e7845befe507c2e5a209ddb81db7fbb87a26f698f3989c89a7307a7ec7734da8
|
| 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 sha256:9fab8d2be65705ddf8fd180ded57b6478878739f8dbb13f64eb5ba4b9ac44e39
|
| 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,
|
|
@@ -2978,6 +2978,24 @@
|
|
| 2978 |
"mean_token_accuracy": 0.6498158782720566,
|
| 2979 |
"num_tokens": 6016722.0,
|
| 2980 |
"step": 1650
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2981 |
}
|
| 2982 |
],
|
| 2983 |
"logging_steps": 5,
|
|
@@ -2997,7 +3015,7 @@
|
|
| 2997 |
"attributes": {}
|
| 2998 |
}
|
| 2999 |
},
|
| 3000 |
-
"total_flos": 3.
|
| 3001 |
"train_batch_size": 4,
|
| 3002 |
"trial_name": null,
|
| 3003 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 12.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1660,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2978 |
"mean_token_accuracy": 0.6498158782720566,
|
| 2979 |
"num_tokens": 6016722.0,
|
| 2980 |
"step": 1650
|
| 2981 |
+
},
|
| 2982 |
+
{
|
| 2983 |
+
"epoch": 12.73076923076923,
|
| 2984 |
+
"grad_norm": 0.0,
|
| 2985 |
+
"learning_rate": 4.173e-05,
|
| 2986 |
+
"loss": 1.6561,
|
| 2987 |
+
"mean_token_accuracy": 0.6655506461858749,
|
| 2988 |
+
"num_tokens": 6035815.0,
|
| 2989 |
+
"step": 1655
|
| 2990 |
+
},
|
| 2991 |
+
{
|
| 2992 |
+
"epoch": 12.76923076923077,
|
| 2993 |
+
"grad_norm": 0.0,
|
| 2994 |
+
"learning_rate": 4.1705e-05,
|
| 2995 |
+
"loss": 1.7659,
|
| 2996 |
+
"mean_token_accuracy": 0.6420869499444961,
|
| 2997 |
+
"num_tokens": 6053674.0,
|
| 2998 |
+
"step": 1660
|
| 2999 |
}
|
| 3000 |
],
|
| 3001 |
"logging_steps": 5,
|
|
|
|
| 3015 |
"attributes": {}
|
| 3016 |
}
|
| 3017 |
},
|
| 3018 |
+
"total_flos": 3.066641376981811e+17,
|
| 3019 |
"train_batch_size": 4,
|
| 3020 |
"trial_name": null,
|
| 3021 |
"trial_params": null
|