tuanna08go
commited on
Commit
•
6dff7b7
1
Parent(s):
a0b4a72
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 50503544
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd4c1fe439652e9ec64da9ba79512304a425ecc8cc660297071c9205c0454cd1
|
3 |
size 50503544
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 25986148
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c0f3485052cc311c652f6053f8bb16cd0d969d238f42c6b87557c4442d79e8e
|
3 |
size 25986148
|
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 sha256:6f4796865ede106812b09fd8ba4d4deaa9bc7a01436139b627e5afd95faa1c43
|
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": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -58,6 +58,49 @@
|
|
58 |
"eval_samples_per_second": 5.805,
|
59 |
"eval_steps_per_second": 5.805,
|
60 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
61 |
}
|
62 |
],
|
63 |
"logging_steps": 5,
|
@@ -72,12 +115,12 @@
|
|
72 |
"should_evaluate": false,
|
73 |
"should_log": false,
|
74 |
"should_save": true,
|
75 |
-
"should_training_stop":
|
76 |
},
|
77 |
"attributes": {}
|
78 |
}
|
79 |
},
|
80 |
-
"total_flos":
|
81 |
"train_batch_size": 1,
|
82 |
"trial_name": null,
|
83 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0040551500405515,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
58 |
"eval_samples_per_second": 5.805,
|
59 |
"eval_steps_per_second": 5.805,
|
60 |
"step": 25
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 0.0024330900243309003,
|
64 |
+
"grad_norm": 3.194694995880127,
|
65 |
+
"learning_rate": 5e-05,
|
66 |
+
"loss": 1.216,
|
67 |
+
"step": 30
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 0.00283860502838605,
|
71 |
+
"grad_norm": 0.823891818523407,
|
72 |
+
"learning_rate": 3.086582838174551e-05,
|
73 |
+
"loss": 0.5,
|
74 |
+
"step": 35
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.0032441200324412004,
|
78 |
+
"grad_norm": 0.46792903542518616,
|
79 |
+
"learning_rate": 1.4644660940672627e-05,
|
80 |
+
"loss": 1.209,
|
81 |
+
"step": 40
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.0036496350364963502,
|
85 |
+
"grad_norm": 0.7259841561317444,
|
86 |
+
"learning_rate": 3.8060233744356633e-06,
|
87 |
+
"loss": 1.5031,
|
88 |
+
"step": 45
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.0040551500405515,
|
92 |
+
"grad_norm": 81.30354309082031,
|
93 |
+
"learning_rate": 0.0,
|
94 |
+
"loss": 1.4401,
|
95 |
+
"step": 50
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 0.0040551500405515,
|
99 |
+
"eval_loss": 1.422434687614441,
|
100 |
+
"eval_runtime": 236.3994,
|
101 |
+
"eval_samples_per_second": 5.795,
|
102 |
+
"eval_steps_per_second": 5.795,
|
103 |
+
"step": 50
|
104 |
}
|
105 |
],
|
106 |
"logging_steps": 5,
|
|
|
115 |
"should_evaluate": false,
|
116 |
"should_log": false,
|
117 |
"should_save": true,
|
118 |
+
"should_training_stop": true
|
119 |
},
|
120 |
"attributes": {}
|
121 |
}
|
122 |
},
|
123 |
+
"total_flos": 643355482521600.0,
|
124 |
"train_batch_size": 1,
|
125 |
"trial_name": null,
|
126 |
"trial_params": null
|