Training in progress, step 6, 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:d00a248eb35ed5aac9c7053a56e57572c5f1438e9ed06d294e826d9c414cfe55
|
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:acb4e7ea22dd1f044ef8e8e588a1f2fe75a5f1b488a64e6a705a0b482b2a5bd5
|
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:ae38cf2194ed88a3e50c326d9909c363e635b906ebae66a7cef76ae4b031fef7
|
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 sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
|
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,
|
@@ -59,6 +59,28 @@
|
|
59 |
"eval_samples_per_second": 5.352,
|
60 |
"eval_steps_per_second": 5.352,
|
61 |
"step": 4
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
}
|
63 |
],
|
64 |
"logging_steps": 1,
|
@@ -78,7 +100,7 @@
|
|
78 |
"attributes": {}
|
79 |
}
|
80 |
},
|
81 |
-
"total_flos":
|
82 |
"train_batch_size": 1,
|
83 |
"trial_name": null,
|
84 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0036616065298649783,
|
5 |
"eval_steps": 2,
|
6 |
+
"global_step": 6,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
59 |
"eval_samples_per_second": 5.352,
|
60 |
"eval_steps_per_second": 5.352,
|
61 |
"step": 4
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.003051338774887482,
|
65 |
+
"grad_norm": 3.312035322189331,
|
66 |
+
"learning_rate": 0.0001,
|
67 |
+
"loss": 3.6057,
|
68 |
+
"step": 5
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.0036616065298649783,
|
72 |
+
"grad_norm": 4.2615509033203125,
|
73 |
+
"learning_rate": 0.00012,
|
74 |
+
"loss": 3.8022,
|
75 |
+
"step": 6
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.0036616065298649783,
|
79 |
+
"eval_loss": 3.571681022644043,
|
80 |
+
"eval_runtime": 126.1429,
|
81 |
+
"eval_samples_per_second": 5.47,
|
82 |
+
"eval_steps_per_second": 5.47,
|
83 |
+
"step": 6
|
84 |
}
|
85 |
],
|
86 |
"logging_steps": 1,
|
|
|
100 |
"attributes": {}
|
101 |
}
|
102 |
},
|
103 |
+
"total_flos": 842702637760512.0,
|
104 |
"train_batch_size": 1,
|
105 |
"trial_name": null,
|
106 |
"trial_params": null
|