Training in progress, step 300, 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 6304192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:859d509ae70182d49878ff4751bc8679bf39dee599040eb0c409f9326808122e
|
3 |
size 6304192
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00fd8f919a441e01cb02d3ba5683a8bc7e2f7e91f8dbd99958eac172510a2e6f
|
3 |
+
size 12639429
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adc62614d66705b8b13a0d65984d823126f5707ef0d8b71f73a02375c1eb0a11
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -35,6 +35,20 @@
|
|
35 |
"eval_samples_per_second": 15.264,
|
36 |
"eval_steps_per_second": 1.914,
|
37 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
}
|
39 |
],
|
40 |
"logging_steps": 100,
|
@@ -42,7 +56,7 @@
|
|
42 |
"num_input_tokens_seen": 0,
|
43 |
"num_train_epochs": 3,
|
44 |
"save_steps": 100,
|
45 |
-
"total_flos":
|
46 |
"trial_name": null,
|
47 |
"trial_params": null
|
48 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.3053778409957886,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-300",
|
4 |
+
"epoch": 0.4,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 300,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
35 |
"eval_samples_per_second": 15.264,
|
36 |
"eval_steps_per_second": 1.914,
|
37 |
"step": 200
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.4,
|
41 |
+
"learning_rate": 0.0002,
|
42 |
+
"loss": 1.1374,
|
43 |
+
"step": 300
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 0.4,
|
47 |
+
"eval_loss": 1.3053778409957886,
|
48 |
+
"eval_runtime": 126.588,
|
49 |
+
"eval_samples_per_second": 15.246,
|
50 |
+
"eval_steps_per_second": 1.912,
|
51 |
+
"step": 300
|
52 |
}
|
53 |
],
|
54 |
"logging_steps": 100,
|
|
|
56 |
"num_input_tokens_seen": 0,
|
57 |
"num_train_epochs": 3,
|
58 |
"save_steps": 100,
|
59 |
+
"total_flos": 1.0639944335081472e+16,
|
60 |
"trial_name": null,
|
61 |
"trial_params": null
|
62 |
}
|