Commit
•
0dd34fd
1
Parent(s):
bc4502b
Training in progress, step 9000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267835644
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39c0c3e429059596e8f8f20164b6692dddc22cd098b352d3665253e5fdbcfc91
|
3 |
size 267835644
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535733434
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c01892709dc5774539f91fe55711e1975ef99a65bedc34693c03ce7c7bf9d37
|
3 |
size 535733434
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5de4fbb1a4b28f7fc3108f426c0a660a8944f6d88933dbfb3727dcf48844484
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fc78139ebcfada68990564fb6a028a79c77713a52b6e3d0b599cebfd1682acb
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.7183207652218417,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-8000",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -159,6 +159,25 @@
|
|
159 |
"eval_samples_per_second": 87.985,
|
160 |
"eval_steps_per_second": 10.998,
|
161 |
"step": 8000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
162 |
}
|
163 |
],
|
164 |
"logging_steps": 1000,
|
@@ -178,7 +197,7 @@
|
|
178 |
"attributes": {}
|
179 |
}
|
180 |
},
|
181 |
-
"total_flos":
|
182 |
"train_batch_size": 8,
|
183 |
"trial_name": null,
|
184 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.7183207652218417,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-8000",
|
4 |
+
"epoch": 0.9536929108826958,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 9000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
159 |
"eval_samples_per_second": 87.985,
|
160 |
"eval_steps_per_second": 10.998,
|
161 |
"step": 8000
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.9536929108826958,
|
165 |
+
"grad_norm": 4.955699920654297,
|
166 |
+
"learning_rate": 9.094492383082987e-06,
|
167 |
+
"loss": 0.4648,
|
168 |
+
"step": 9000
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 0.9536929108826958,
|
172 |
+
"eval_accuracy": 0.7167832167832168,
|
173 |
+
"eval_f1": 0.7085336559753441,
|
174 |
+
"eval_loss": 0.8246528506278992,
|
175 |
+
"eval_precision": 0.7230635739304796,
|
176 |
+
"eval_recall": 0.7167832167832168,
|
177 |
+
"eval_runtime": 26.0039,
|
178 |
+
"eval_samples_per_second": 87.987,
|
179 |
+
"eval_steps_per_second": 10.998,
|
180 |
+
"step": 9000
|
181 |
}
|
182 |
],
|
183 |
"logging_steps": 1000,
|
|
|
197 |
"attributes": {}
|
198 |
}
|
199 |
},
|
200 |
+
"total_flos": 8735478289285824.0,
|
201 |
"train_batch_size": 8,
|
202 |
"trial_name": null,
|
203 |
"trial_params": null
|