Training in progress, step 2300, 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:d684ecd05014a6e4b865abee492e26b6554b30cf4236772cae188cfdf54a31c5
|
| 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 sha256:1b84fdd5186fecc2135d66ce5e90b9d970c637f25b54ce96dbf51a2bc64bafa7
|
| 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 sha256:06ce8938497c715c652afc1b066216edbd2243711a6c62a4aabb5982c4cd971f
|
| 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": 17.
|
| 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,
|
|
@@ -4130,6 +4130,24 @@
|
|
| 4130 |
"mean_token_accuracy": 0.6476155072450638,
|
| 4131 |
"num_tokens": 8354016.0,
|
| 4132 |
"step": 2290
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4133 |
}
|
| 4134 |
],
|
| 4135 |
"logging_steps": 5,
|
|
@@ -4149,7 +4167,7 @@
|
|
| 4149 |
"attributes": {}
|
| 4150 |
}
|
| 4151 |
},
|
| 4152 |
-
"total_flos": 4.
|
| 4153 |
"train_batch_size": 4,
|
| 4154 |
"trial_name": null,
|
| 4155 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 17.692307692307693,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2300,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4130 |
"mean_token_accuracy": 0.6476155072450638,
|
| 4131 |
"num_tokens": 8354016.0,
|
| 4132 |
"step": 2290
|
| 4133 |
+
},
|
| 4134 |
+
{
|
| 4135 |
+
"epoch": 17.653846153846153,
|
| 4136 |
+
"grad_norm": 0.0,
|
| 4137 |
+
"learning_rate": 3.853e-05,
|
| 4138 |
+
"loss": 1.7454,
|
| 4139 |
+
"mean_token_accuracy": 0.6534331560134887,
|
| 4140 |
+
"num_tokens": 8371707.0,
|
| 4141 |
+
"step": 2295
|
| 4142 |
+
},
|
| 4143 |
+
{
|
| 4144 |
+
"epoch": 17.692307692307693,
|
| 4145 |
+
"grad_norm": 0.0,
|
| 4146 |
+
"learning_rate": 3.8505000000000005e-05,
|
| 4147 |
+
"loss": 1.7394,
|
| 4148 |
+
"mean_token_accuracy": 0.6537044525146485,
|
| 4149 |
+
"num_tokens": 8389636.0,
|
| 4150 |
+
"step": 2300
|
| 4151 |
}
|
| 4152 |
],
|
| 4153 |
"logging_steps": 5,
|
|
|
|
| 4167 |
"attributes": {}
|
| 4168 |
}
|
| 4169 |
},
|
| 4170 |
+
"total_flos": 4.2518737187536896e+17,
|
| 4171 |
"train_batch_size": 4,
|
| 4172 |
"trial_name": null,
|
| 4173 |
"trial_params": null
|