tuanna08go
commited on
Training in progress, step 50, 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 36981072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22e76835874c179361197ebc62cd61803e3c4693d5ffe09469cbdb1cb7fee3ab
|
3 |
size 36981072
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 19859140
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf349c5a8a9d634cabb4b4215af87acd94818f5b55059aa0f8202c7fabf26274
|
3 |
size 19859140
|
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 sha256:32d2d71e55139139716945de50eaa3f9c08bb44e155b796f3b6c746fa78b2ecc
|
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:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
|
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,
|
@@ -60,6 +60,36 @@
|
|
60 |
"eval_samples_per_second": 26.956,
|
61 |
"eval_steps_per_second": 3.388,
|
62 |
"step": 30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
}
|
64 |
],
|
65 |
"logging_steps": 10,
|
@@ -74,12 +104,12 @@
|
|
74 |
"should_evaluate": false,
|
75 |
"should_log": false,
|
76 |
"should_save": true,
|
77 |
-
"should_training_stop":
|
78 |
},
|
79 |
"attributes": {}
|
80 |
}
|
81 |
},
|
82 |
-
"total_flos":
|
83 |
"train_batch_size": 8,
|
84 |
"trial_name": null,
|
85 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.45558086560364464,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
60 |
"eval_samples_per_second": 26.956,
|
61 |
"eval_steps_per_second": 3.388,
|
62 |
"step": 30
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.36446469248291574,
|
66 |
+
"grad_norm": 2.657161235809326,
|
67 |
+
"learning_rate": 1.0332332985438248e-05,
|
68 |
+
"loss": 0.4525,
|
69 |
+
"step": 40
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.36446469248291574,
|
73 |
+
"eval_loss": 0.3867056369781494,
|
74 |
+
"eval_runtime": 27.7318,
|
75 |
+
"eval_samples_per_second": 26.684,
|
76 |
+
"eval_steps_per_second": 3.354,
|
77 |
+
"step": 40
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 0.45558086560364464,
|
81 |
+
"grad_norm": 0.9272085428237915,
|
82 |
+
"learning_rate": 0.0,
|
83 |
+
"loss": 0.3723,
|
84 |
+
"step": 50
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.45558086560364464,
|
88 |
+
"eval_loss": 0.37940335273742676,
|
89 |
+
"eval_runtime": 27.5173,
|
90 |
+
"eval_samples_per_second": 26.892,
|
91 |
+
"eval_steps_per_second": 3.38,
|
92 |
+
"step": 50
|
93 |
}
|
94 |
],
|
95 |
"logging_steps": 10,
|
|
|
104 |
"should_evaluate": false,
|
105 |
"should_log": false,
|
106 |
"should_save": true,
|
107 |
+
"should_training_stop": true
|
108 |
},
|
109 |
"attributes": {}
|
110 |
}
|
111 |
},
|
112 |
+
"total_flos": 5.136884414860493e+16,
|
113 |
"train_batch_size": 8,
|
114 |
"trial_name": null,
|
115 |
"trial_params": null
|