Training in progress, step 7, 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 42002136
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63d8c3b68381200eaae0ee160b6272260b14c37456b46ab131ab58cb0ae45346
|
3 |
size 42002136
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 21822612
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2da4600274e2621c44698fff6a5895b5f50f89b592c87a8a47f898e8ff63cdd8
|
3 |
size 21822612
|
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 sha256:524f5dcf863332849f6d35a5cf59cdd63b66a70a4c6791080f7ca3f961f4753f
|
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 sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
|
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": 2,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -81,6 +81,13 @@
|
|
81 |
"eval_samples_per_second": 5.47,
|
82 |
"eval_steps_per_second": 5.47,
|
83 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
}
|
85 |
],
|
86 |
"logging_steps": 1,
|
@@ -95,12 +102,12 @@
|
|
95 |
"should_evaluate": false,
|
96 |
"should_log": false,
|
97 |
"should_save": true,
|
98 |
-
"should_training_stop":
|
99 |
},
|
100 |
"attributes": {}
|
101 |
}
|
102 |
},
|
103 |
-
"total_flos":
|
104 |
"train_batch_size": 1,
|
105 |
"trial_name": null,
|
106 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.004271874284842474,
|
5 |
"eval_steps": 2,
|
6 |
+
"global_step": 7,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
81 |
"eval_samples_per_second": 5.47,
|
82 |
"eval_steps_per_second": 5.47,
|
83 |
"step": 6
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.004271874284842474,
|
87 |
+
"grad_norm": 2.7097175121307373,
|
88 |
+
"learning_rate": 0.00014,
|
89 |
+
"loss": 2.9957,
|
90 |
+
"step": 7
|
91 |
}
|
92 |
],
|
93 |
"logging_steps": 1,
|
|
|
102 |
"should_evaluate": false,
|
103 |
"should_log": false,
|
104 |
"should_save": true,
|
105 |
+
"should_training_stop": true
|
106 |
},
|
107 |
"attributes": {}
|
108 |
}
|
109 |
},
|
110 |
+
"total_flos": 981229098762240.0,
|
111 |
"train_batch_size": 1,
|
112 |
"trial_name": null,
|
113 |
"trial_params": null
|