Training in progress, epoch 3, checkpoint
Browse files- last-checkpoint/model-00001-of-00002.safetensors +1 -1
- last-checkpoint/model-00002-of-00002.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +18 -4
last-checkpoint/model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4993448880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33fd187ec114814006c2e75653477635f3d02bf4d789aedc35ab929c9490ed19
|
3 |
size 4993448880
|
last-checkpoint/model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1180663192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cd1b7f0f3fd145c372cf886b9300ed599f268c2fa16bae15a22687b10fb8a48
|
3 |
size 1180663192
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3137574192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ddd374e355098aa97ab43898b119198d989e8dd806dd88accd4f3c4f0705e70
|
3 |
size 3137574192
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2f95e28a3f2bfade18a7534d600bfb77e2fbc0925e92565dcc4bf4fc6a63093
|
3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:504b793d036b7514e777c933f30336833926eca6cd89f5ec06a8bbf57ab6a775
|
3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6524d9a1e2c33f433bd0661a5b1b62e4b8815993b01362c8edc3116f7076c706
|
3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b85a1598213ff70c00c9c0d72e84803908cdf6961c3b07493ae8d4a18a5f42d
|
3 |
size 15024
|
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 sha256:6e16ea8944744cbadfbfc8bfb1885278f290c3a88899510abed4b61d696290a5
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 18.565923091763654,
|
3 |
"best_model_checkpoint": "./models/rootflo/fauna-v3.6/checkpoint-259",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -55,6 +55,20 @@
|
|
55 |
"eval_samples_per_second": 1.676,
|
56 |
"eval_steps_per_second": 0.004,
|
57 |
"step": 388
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
}
|
59 |
],
|
60 |
"logging_steps": 100,
|
@@ -78,12 +92,12 @@
|
|
78 |
"should_evaluate": false,
|
79 |
"should_log": false,
|
80 |
"should_save": true,
|
81 |
-
"should_training_stop":
|
82 |
},
|
83 |
"attributes": {}
|
84 |
}
|
85 |
},
|
86 |
-
"total_flos": 1.
|
87 |
"train_batch_size": 96,
|
88 |
"trial_name": null,
|
89 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 18.565923091763654,
|
3 |
"best_model_checkpoint": "./models/rootflo/fauna-v3.6/checkpoint-259",
|
4 |
+
"epoch": 3.9845559845559846,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 516,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
55 |
"eval_samples_per_second": 1.676,
|
56 |
"eval_steps_per_second": 0.004,
|
57 |
"step": 388
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 3.088803088803089,
|
61 |
+
"grad_norm": 0.32632899284362793,
|
62 |
+
"learning_rate": 3.656067158363546e-07,
|
63 |
+
"loss": 0.2347,
|
64 |
+
"step": 400
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 3.861003861003861,
|
68 |
+
"grad_norm": 0.3226456344127655,
|
69 |
+
"learning_rate": 8.229706450227802e-09,
|
70 |
+
"loss": 0.2285,
|
71 |
+
"step": 500
|
72 |
}
|
73 |
],
|
74 |
"logging_steps": 100,
|
|
|
92 |
"should_evaluate": false,
|
93 |
"should_log": false,
|
94 |
"should_save": true,
|
95 |
+
"should_training_stop": true
|
96 |
},
|
97 |
"attributes": {}
|
98 |
}
|
99 |
},
|
100 |
+
"total_flos": 1.3463878146985915e+21,
|
101 |
"train_batch_size": 96,
|
102 |
"trial_name": null,
|
103 |
"trial_params": null
|