Training in progress, step 5060, 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:acaa86d5efbd4f41649888c853e7795d581e64b9c55a6ea2b1a049e6d58dd521
|
| 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 sha256:9335c0493e5cafdcd4f2d97bba8ba4a49f0fcab1ccefdbf1146c9c7370b74c40
|
| 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 sha256:035f251a274c496ba95a9521172855f95b7c358016a5bf755b09172e784b0c4b
|
| 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": 38.
|
| 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,
|
|
@@ -9098,6 +9098,24 @@
|
|
| 9098 |
"mean_token_accuracy": 0.6461145460605622,
|
| 9099 |
"num_tokens": 18416605.0,
|
| 9100 |
"step": 5050
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9101 |
}
|
| 9102 |
],
|
| 9103 |
"logging_steps": 5,
|
|
@@ -9117,7 +9135,7 @@
|
|
| 9117 |
"attributes": {}
|
| 9118 |
}
|
| 9119 |
},
|
| 9120 |
-
"total_flos": 9.
|
| 9121 |
"train_batch_size": 4,
|
| 9122 |
"trial_name": null,
|
| 9123 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 38.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5060,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9098 |
"mean_token_accuracy": 0.6461145460605622,
|
| 9099 |
"num_tokens": 18416605.0,
|
| 9100 |
"step": 5050
|
| 9101 |
+
},
|
| 9102 |
+
{
|
| 9103 |
+
"epoch": 38.88461538461539,
|
| 9104 |
+
"grad_norm": 0.0,
|
| 9105 |
+
"learning_rate": 2.473e-05,
|
| 9106 |
+
"loss": 1.7961,
|
| 9107 |
+
"mean_token_accuracy": 0.6413571745157242,
|
| 9108 |
+
"num_tokens": 18434448.0,
|
| 9109 |
+
"step": 5055
|
| 9110 |
+
},
|
| 9111 |
+
{
|
| 9112 |
+
"epoch": 38.92307692307692,
|
| 9113 |
+
"grad_norm": 0.0,
|
| 9114 |
+
"learning_rate": 2.4705e-05,
|
| 9115 |
+
"loss": 1.7132,
|
| 9116 |
+
"mean_token_accuracy": 0.6524721384048462,
|
| 9117 |
+
"num_tokens": 18453025.0,
|
| 9118 |
+
"step": 5060
|
| 9119 |
}
|
| 9120 |
],
|
| 9121 |
"logging_steps": 5,
|
|
|
|
| 9135 |
"attributes": {}
|
| 9136 |
}
|
| 9137 |
},
|
| 9138 |
+
"total_flos": 9.350364196424909e+17,
|
| 9139 |
"train_batch_size": 4,
|
| 9140 |
"trial_name": null,
|
| 9141 |
"trial_params": null
|