Training in progress, step 3, 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 41581360
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a368b0bf1794511f2f8fbb03f694b00ff048b15bf1d0dad4836ef8ebf86cde34
|
3 |
size 41581360
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 21505540
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab17512ef5120fe4b1586795bd7d5edf8d94d2e601eda05116ec7fe84ccb39d6
|
3 |
size 21505540
|
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 sha256:7de467893e672a801a7f1cdb08392e9d44e3a212844f5c512ebfc1cfea50e9b1
|
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:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
|
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":
|
5 |
"eval_steps": 1,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -37,6 +37,21 @@
|
|
37 |
"eval_samples_per_second": 55.692,
|
38 |
"eval_steps_per_second": 33.415,
|
39 |
"step": 2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
}
|
41 |
],
|
42 |
"logging_steps": 1,
|
@@ -51,12 +66,12 @@
|
|
51 |
"should_evaluate": false,
|
52 |
"should_log": false,
|
53 |
"should_save": true,
|
54 |
-
"should_training_stop":
|
55 |
},
|
56 |
"attributes": {}
|
57 |
}
|
58 |
},
|
59 |
-
"total_flos":
|
60 |
"train_batch_size": 2,
|
61 |
"trial_name": null,
|
62 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.108695652173913,
|
5 |
"eval_steps": 1,
|
6 |
+
"global_step": 3,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
37 |
"eval_samples_per_second": 55.692,
|
38 |
"eval_steps_per_second": 33.415,
|
39 |
"step": 2
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.108695652173913,
|
43 |
+
"grad_norm": 61.87843704223633,
|
44 |
+
"learning_rate": 3e-05,
|
45 |
+
"loss": 25.8279,
|
46 |
+
"step": 3
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 1.108695652173913,
|
50 |
+
"eval_loss": 18.228900909423828,
|
51 |
+
"eval_runtime": 0.0897,
|
52 |
+
"eval_samples_per_second": 55.754,
|
53 |
+
"eval_steps_per_second": 33.453,
|
54 |
+
"step": 3
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 1,
|
|
|
66 |
"should_evaluate": false,
|
67 |
"should_log": false,
|
68 |
"should_save": true,
|
69 |
+
"should_training_stop": true
|
70 |
},
|
71 |
"attributes": {}
|
72 |
}
|
73 |
},
|
74 |
+
"total_flos": 612619230117888.0,
|
75 |
"train_batch_size": 2,
|
76 |
"trial_name": null,
|
77 |
"trial_params": null
|