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 54549088
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5577a8941e77d336743275e7da5e4cdcd23d32aad241c80b2b853600d3c725ac
|
3 |
size 54549088
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 17257078
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d020d6cbc209ce0f314ca0a8003eb033cdbf9688d7859f2582c9fcbacae60e03
|
3 |
size 17257078
|
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 sha256:7a1e291d8537288b0a36329a39b39607cb44b500e86d0efc23d63b267b05d63d
|
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 2080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44e6d52016f274ad8f80c1ee8eed78e2181c51bc1f820b1142e826ce6518f1c0
|
3 |
size 2080
|
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": 6.465,
|
38 |
"eval_steps_per_second": 6.465,
|
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": 1,
|
61 |
"trial_name": null,
|
62 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0001094715716012498,
|
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": 6.465,
|
38 |
"eval_steps_per_second": 6.465,
|
39 |
"step": 2
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.0001094715716012498,
|
43 |
+
"grad_norm": 3.4407198429107666,
|
44 |
+
"learning_rate": 0.003000000026077032,
|
45 |
+
"loss": 1.9633,
|
46 |
+
"step": 3
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.0001094715716012498,
|
50 |
+
"eval_loss": 3.4792585372924805,
|
51 |
+
"eval_runtime": 1849.5831,
|
52 |
+
"eval_samples_per_second": 6.239,
|
53 |
+
"eval_steps_per_second": 6.239,
|
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": 217473780547584.0,
|
75 |
"train_batch_size": 1,
|
76 |
"trial_name": null,
|
77 |
"trial_params": null
|