tuanna08go
commited on
Commit
•
24c99ad
1
Parent(s):
9897889
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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a4926c85de91288fe6f06d97b943f1271f14965c6a45e5489ff1160a470a4d7
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 85723284
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f644afaeb35592d20ad4050dfcaa12c4bd8176c898486644fac6d4587756ac88
|
3 |
size 85723284
|
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 sha256:0403941aa6de2eb4baf35cb227f7f96455fada34654996d73ae5e536d2760774
|
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": 2.728,
|
59 |
"eval_steps_per_second": 2.728,
|
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": 0.003032749908069768,
|
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": 2.728,
|
59 |
"eval_steps_per_second": 2.728,
|
60 |
"step": 25
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 0.001819649944841861,
|
64 |
+
"grad_norm": 1.9589847326278687,
|
65 |
+
"learning_rate": 3.705904774487396e-05,
|
66 |
+
"loss": 1.6359,
|
67 |
+
"step": 30
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 0.002122924935648838,
|
71 |
+
"grad_norm": 1.4695641994476318,
|
72 |
+
"learning_rate": 2.2221488349019903e-05,
|
73 |
+
"loss": 1.6006,
|
74 |
+
"step": 35
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.002426199926455815,
|
78 |
+
"grad_norm": 1.7299948930740356,
|
79 |
+
"learning_rate": 1.0332332985438248e-05,
|
80 |
+
"loss": 1.6185,
|
81 |
+
"step": 40
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.0027294749172627917,
|
85 |
+
"grad_norm": 1.8927239179611206,
|
86 |
+
"learning_rate": 2.653493525244721e-06,
|
87 |
+
"loss": 1.586,
|
88 |
+
"step": 45
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.003032749908069768,
|
92 |
+
"grad_norm": 1.600250482559204,
|
93 |
+
"learning_rate": 0.0,
|
94 |
+
"loss": 1.4815,
|
95 |
+
"step": 50
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 0.003032749908069768,
|
99 |
+
"eval_loss": NaN,
|
100 |
+
"eval_runtime": 21453.8519,
|
101 |
+
"eval_samples_per_second": 2.732,
|
102 |
+
"eval_steps_per_second": 2.732,
|
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": 1.483774567120896e+17,
|
124 |
"train_batch_size": 1,
|
125 |
"trial_name": null,
|
126 |
"trial_params": null
|