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 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b17e7e41bdc0d5675854795de4be6453c3fabfeb287882ee534898f43327e4e
|
3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43122580
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:652f3471522690266c4aa85a37c08261c3d955fc3b53a3a91146819bcffe1a09
|
3 |
size 43122580
|
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:b9b32a31b90c640b6f3edbb6f5edfd55f2a05c8f726be41404fdb7ef23099e0b
|
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,
|
@@ -88,6 +88,43 @@
|
|
88 |
"learning_rate": 3.086582838174551e-05,
|
89 |
"loss": 0.2954,
|
90 |
"step": 35
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
91 |
}
|
92 |
],
|
93 |
"logging_steps": 5,
|
@@ -102,12 +139,12 @@
|
|
102 |
"should_evaluate": false,
|
103 |
"should_log": false,
|
104 |
"should_save": true,
|
105 |
-
"should_training_stop":
|
106 |
},
|
107 |
"attributes": {}
|
108 |
}
|
109 |
},
|
110 |
-
"total_flos":
|
111 |
"train_batch_size": 2,
|
112 |
"trial_name": null,
|
113 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.012948336138806164,
|
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,
|
|
|
88 |
"learning_rate": 3.086582838174551e-05,
|
89 |
"loss": 0.2954,
|
90 |
"step": 35
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.01035866891104493,
|
94 |
+
"grad_norm": 0.755368709564209,
|
95 |
+
"learning_rate": 1.4644660940672627e-05,
|
96 |
+
"loss": 0.2693,
|
97 |
+
"step": 40
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.01035866891104493,
|
101 |
+
"eval_loss": 0.28383180499076843,
|
102 |
+
"eval_runtime": 109.5571,
|
103 |
+
"eval_samples_per_second": 14.842,
|
104 |
+
"eval_steps_per_second": 7.421,
|
105 |
+
"step": 40
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.011653502524925547,
|
109 |
+
"grad_norm": 0.9192548394203186,
|
110 |
+
"learning_rate": 3.8060233744356633e-06,
|
111 |
+
"loss": 0.2735,
|
112 |
+
"step": 45
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 0.012948336138806164,
|
116 |
+
"grad_norm": 1.1631362438201904,
|
117 |
+
"learning_rate": 0.0,
|
118 |
+
"loss": 0.2861,
|
119 |
+
"step": 50
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 0.012948336138806164,
|
123 |
+
"eval_loss": 0.2751847803592682,
|
124 |
+
"eval_runtime": 109.3309,
|
125 |
+
"eval_samples_per_second": 14.872,
|
126 |
+
"eval_steps_per_second": 7.436,
|
127 |
+
"step": 50
|
128 |
}
|
129 |
],
|
130 |
"logging_steps": 5,
|
|
|
139 |
"should_evaluate": false,
|
140 |
"should_log": false,
|
141 |
"should_save": true,
|
142 |
+
"should_training_stop": true
|
143 |
},
|
144 |
"attributes": {}
|
145 |
}
|
146 |
},
|
147 |
+
"total_flos": 9294060346933248.0,
|
148 |
"train_batch_size": 2,
|
149 |
"trial_name": null,
|
150 |
"trial_params": null
|