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 125248064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f7fcf7d01f66123b7fbfc7e30882d941cfd57e1b61302635e775014e97fea85
|
3 |
size 125248064
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 64219860
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bd37a357343c2b5d408f9964b7867f8894e44a9264dd38e6a2e5dea0068933a
|
3 |
size 64219860
|
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 sha256:064297d010231bc9ba87d05c6184aa47455d8655363a0f6bbb29596d61eefbf6
|
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:c9b23fe3d7c8cff984a05b7865b1b491bac693fd2f496a4e0e24b70ad75a25bd
|
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,
|
@@ -54,6 +54,14 @@
|
|
54 |
"eval_samples_per_second": 5.655,
|
55 |
"eval_steps_per_second": 2.828,
|
56 |
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
}
|
58 |
],
|
59 |
"logging_steps": 40,
|
@@ -68,12 +76,12 @@
|
|
68 |
"should_evaluate": false,
|
69 |
"should_log": false,
|
70 |
"should_save": true,
|
71 |
-
"should_training_stop":
|
72 |
},
|
73 |
"attributes": {}
|
74 |
}
|
75 |
},
|
76 |
-
"total_flos":
|
77 |
"train_batch_size": 2,
|
78 |
"trial_name": null,
|
79 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.04796738218011752,
|
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,
|
|
|
54 |
"eval_samples_per_second": 5.655,
|
55 |
"eval_steps_per_second": 2.828,
|
56 |
"step": 40
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.04796738218011752,
|
60 |
+
"eval_loss": 1.7664101123809814,
|
61 |
+
"eval_runtime": 308.078,
|
62 |
+
"eval_samples_per_second": 5.7,
|
63 |
+
"eval_steps_per_second": 2.85,
|
64 |
+
"step": 50
|
65 |
}
|
66 |
],
|
67 |
"logging_steps": 40,
|
|
|
76 |
"should_evaluate": false,
|
77 |
"should_log": false,
|
78 |
"should_save": true,
|
79 |
+
"should_training_stop": true
|
80 |
},
|
81 |
"attributes": {}
|
82 |
}
|
83 |
},
|
84 |
+
"total_flos": 6.3324486107136e+16,
|
85 |
"train_batch_size": 2,
|
86 |
"trial_name": null,
|
87 |
"trial_params": null
|