Training in progress, step 108, 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 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c005e206608dc5fbf66d549c294fa449a740d653d42ea6d8165c4424d716d4e
|
3 |
size 83945296
|
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 sha256:7deaf57c0b83dbdcbd59877c93f9b24e484e1362e5f813d70c8170eb81ca89e2
|
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 sha256:34b6d2a96b848b624bb72e8637cb9bdeed20b6109b71ac4e397c47502434b277
|
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 sha256:1a6a6cd4d29051dbbd620f5be794d7907f7074bbcf6581f845d14dd274960688
|
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": 27,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -53,6 +53,14 @@
|
|
53 |
"eval_samples_per_second": 15.081,
|
54 |
"eval_steps_per_second": 7.541,
|
55 |
"step": 81
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
}
|
57 |
],
|
58 |
"logging_steps": 40,
|
@@ -72,7 +80,7 @@
|
|
72 |
"attributes": {}
|
73 |
}
|
74 |
},
|
75 |
-
"total_flos":
|
76 |
"train_batch_size": 2,
|
77 |
"trial_name": null,
|
78 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.8078541374474053,
|
5 |
"eval_steps": 27,
|
6 |
+
"global_step": 108,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
53 |
"eval_samples_per_second": 15.081,
|
54 |
"eval_steps_per_second": 7.541,
|
55 |
"step": 81
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 0.8078541374474053,
|
59 |
+
"eval_loss": 2.918757438659668,
|
60 |
+
"eval_runtime": 15.1858,
|
61 |
+
"eval_samples_per_second": 14.882,
|
62 |
+
"eval_steps_per_second": 7.441,
|
63 |
+
"step": 108
|
64 |
}
|
65 |
],
|
66 |
"logging_steps": 40,
|
|
|
80 |
"attributes": {}
|
81 |
}
|
82 |
},
|
83 |
+
"total_flos": 7.571533475296051e+16,
|
84 |
"train_batch_size": 2,
|
85 |
"trial_name": null,
|
86 |
"trial_params": null
|