Training in progress, step 9, 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 48679352
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da987520a32a64b194f9c985e749d8f6e140217684b28b96773b1d21c8e1d24d
|
3 |
size 48679352
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 25152500
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:869fe41744835d67a46c08ecb1369ed0b6e79889b1e6afd6381e86487d322688
|
3 |
size 25152500
|
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:f5be88e0e4febb78e0afca9fa930d343b4e7aef1b9aeff26265a72d7c8c0391a
|
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 sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
|
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": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -65,6 +65,27 @@
|
|
65 |
"learning_rate": 6e-05,
|
66 |
"loss": 1.3162,
|
67 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
68 |
}
|
69 |
],
|
70 |
"logging_steps": 1,
|
@@ -84,7 +105,7 @@
|
|
84 |
"attributes": {}
|
85 |
}
|
86 |
},
|
87 |
-
"total_flos":
|
88 |
"train_batch_size": 1,
|
89 |
"trial_name": null,
|
90 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.15991116046640755,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 9,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
65 |
"learning_rate": 6e-05,
|
66 |
"loss": 1.3162,
|
67 |
"step": 6
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 0.1243753470294281,
|
71 |
+
"grad_norm": 0.8236738443374634,
|
72 |
+
"learning_rate": 7e-05,
|
73 |
+
"loss": 1.4023,
|
74 |
+
"step": 7
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.14214325374791784,
|
78 |
+
"grad_norm": 0.9258612394332886,
|
79 |
+
"learning_rate": 8e-05,
|
80 |
+
"loss": 1.365,
|
81 |
+
"step": 8
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.15991116046640755,
|
85 |
+
"grad_norm": 0.9246096014976501,
|
86 |
+
"learning_rate": 9e-05,
|
87 |
+
"loss": 1.3684,
|
88 |
+
"step": 9
|
89 |
}
|
90 |
],
|
91 |
"logging_steps": 1,
|
|
|
105 |
"attributes": {}
|
106 |
}
|
107 |
},
|
108 |
+
"total_flos": 2504602964459520.0,
|
109 |
"train_batch_size": 1,
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|