tuanna08go
commited on
Training in progress, step 34, 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 608249904
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c03d71f7ab330b18ad346334a241748f2b1444a605f5c518969f069576d47ec4
|
3 |
size 608249904
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43122580
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76ebe3643a2223dc55588522f451fcf84c1f3f26255dde8a61a9e2cef46a77c3
|
3 |
size 43122580
|
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 sha256:0ca28602a8329d58469fb3371a0eb088334bc1b9324ec2b3e34c9885c7b95763
|
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 sha256:1fe247b8abd9f098bbbafb55011dbe010f2fe145118845b911d1500aa9422fe0
|
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": 0
|
5 |
"eval_steps": 7,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -53,6 +53,21 @@
|
|
53 |
"eval_samples_per_second": 18.775,
|
54 |
"eval_steps_per_second": 2.367,
|
55 |
"step": 21
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
}
|
57 |
],
|
58 |
"logging_steps": 10,
|
@@ -67,12 +82,12 @@
|
|
67 |
"should_evaluate": false,
|
68 |
"should_log": false,
|
69 |
"should_save": true,
|
70 |
-
"should_training_stop":
|
71 |
},
|
72 |
"attributes": {}
|
73 |
}
|
74 |
},
|
75 |
-
"total_flos":
|
76 |
"train_batch_size": 8,
|
77 |
"trial_name": null,
|
78 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
"eval_steps": 7,
|
6 |
+
"global_step": 34,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
53 |
"eval_samples_per_second": 18.775,
|
54 |
"eval_steps_per_second": 2.367,
|
55 |
"step": 21
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 0.8235294117647058,
|
59 |
+
"eval_loss": 2.1168278180994093e-05,
|
60 |
+
"eval_runtime": 12.3009,
|
61 |
+
"eval_samples_per_second": 18.698,
|
62 |
+
"eval_steps_per_second": 2.358,
|
63 |
+
"step": 28
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.8823529411764706,
|
67 |
+
"grad_norm": 0.0023900624364614487,
|
68 |
+
"learning_rate": 3.8060233744356633e-06,
|
69 |
+
"loss": 0.0,
|
70 |
+
"step": 30
|
71 |
}
|
72 |
],
|
73 |
"logging_steps": 10,
|
|
|
82 |
"should_evaluate": false,
|
83 |
"should_log": false,
|
84 |
"should_save": true,
|
85 |
+
"should_training_stop": true
|
86 |
},
|
87 |
"attributes": {}
|
88 |
}
|
89 |
},
|
90 |
+
"total_flos": 9.532338273150566e+16,
|
91 |
"train_batch_size": 8,
|
92 |
"trial_name": null,
|
93 |
"trial_params": null
|