Training in progress, step 88, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 97728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91681cc39adfefb90bdea99ca5745b581f4801561d0227fe660b2c43d77ec0dc
|
3 |
size 97728
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 212298
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec4f676d3431bbfbfaeff2ffbc79740e2a9a6c4dba4a0a98b90195be616411c5
|
3 |
size 212298
|
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 sha256:045ee9d5cf40840149ae782fad88c8a05540105615a0bd2b1c43fb04b7d7e58f
|
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 sha256:01a4e7013bdf0cfef44b18348c4082377d680816016af2638e8995bf0bb3c8d9
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.
|
5 |
"eval_steps": 8,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -277,6 +277,35 @@
|
|
277 |
"eval_samples_per_second": 137.482,
|
278 |
"eval_steps_per_second": 69.017,
|
279 |
"step": 80
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
280 |
}
|
281 |
],
|
282 |
"logging_steps": 3,
|
@@ -296,7 +325,7 @@
|
|
296 |
"attributes": {}
|
297 |
}
|
298 |
},
|
299 |
-
"total_flos":
|
300 |
"train_batch_size": 2,
|
301 |
"trial_name": null,
|
302 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.1966101694915254,
|
5 |
"eval_steps": 8,
|
6 |
+
"global_step": 88,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
277 |
"eval_samples_per_second": 137.482,
|
278 |
"eval_steps_per_second": 69.017,
|
279 |
"step": 80
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 1.1016949152542372,
|
283 |
+
"grad_norm": 0.0535203292965889,
|
284 |
+
"learning_rate": 8.047222744854943e-06,
|
285 |
+
"loss": 10.3181,
|
286 |
+
"step": 81
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 1.1423728813559322,
|
290 |
+
"grad_norm": 0.07268232852220535,
|
291 |
+
"learning_rate": 3.6037139304146762e-06,
|
292 |
+
"loss": 10.3939,
|
293 |
+
"step": 84
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.1830508474576271,
|
297 |
+
"grad_norm": 0.0458713173866272,
|
298 |
+
"learning_rate": 9.0502382320653e-07,
|
299 |
+
"loss": 10.3273,
|
300 |
+
"step": 87
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 1.1966101694915254,
|
304 |
+
"eval_loss": 10.348885536193848,
|
305 |
+
"eval_runtime": 1.801,
|
306 |
+
"eval_samples_per_second": 138.257,
|
307 |
+
"eval_steps_per_second": 69.406,
|
308 |
+
"step": 88
|
309 |
}
|
310 |
],
|
311 |
"logging_steps": 3,
|
|
|
325 |
"attributes": {}
|
326 |
}
|
327 |
},
|
328 |
+
"total_flos": 69137241341952.0,
|
329 |
"train_batch_size": 2,
|
330 |
"trial_name": null,
|
331 |
"trial_params": null
|