Training in progress, step 39, 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 65309632
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a543ac9dc81d2b08ab1f285c4b0ddce8742ff4b5ebb4c9c343f0012398fa1c2a
|
3 |
size 65309632
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 33424212
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac4c22cc0834c6e4466b679c38b3bb38c5014e13a6c6b169c1c6a31fcf531643
|
3 |
size 33424212
|
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:b074dd7788a357c83e204bf182c8046b1383eb0a9ff02da64031fe764375a72b
|
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 sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
|
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": 10,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -66,6 +66,28 @@
|
|
66 |
"learning_rate": 6.91341716182545e-05,
|
67 |
"loss": 2.4931,
|
68 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
}
|
70 |
],
|
71 |
"logging_steps": 5,
|
@@ -85,7 +107,7 @@
|
|
85 |
"attributes": {}
|
86 |
}
|
87 |
},
|
88 |
-
"total_flos":
|
89 |
"train_batch_size": 2,
|
90 |
"trial_name": null,
|
91 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.006192687864713589,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 39,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
66 |
"learning_rate": 6.91341716182545e-05,
|
67 |
"loss": 2.4931,
|
68 |
"step": 25
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.004763606049779683,
|
72 |
+
"grad_norm": 45.21467590332031,
|
73 |
+
"learning_rate": 5e-05,
|
74 |
+
"loss": 1.5443,
|
75 |
+
"step": 30
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.004763606049779683,
|
79 |
+
"eval_loss": 0.33188173174858093,
|
80 |
+
"eval_runtime": 280.4106,
|
81 |
+
"eval_samples_per_second": 9.458,
|
82 |
+
"eval_steps_per_second": 4.729,
|
83 |
+
"step": 30
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.00555754039140963,
|
87 |
+
"grad_norm": 19.217050552368164,
|
88 |
+
"learning_rate": 3.086582838174551e-05,
|
89 |
+
"loss": 1.1656,
|
90 |
+
"step": 35
|
91 |
}
|
92 |
],
|
93 |
"logging_steps": 5,
|
|
|
107 |
"attributes": {}
|
108 |
}
|
109 |
},
|
110 |
+
"total_flos": 1.2161961328902144e+16,
|
111 |
"train_batch_size": 2,
|
112 |
"trial_name": null,
|
113 |
"trial_params": null
|