Training in progress, step 120, checkpoint
Browse files- 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/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +62 -18
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 330143034
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd56b63f9d959f90d0f4fafc9d4ceee3e07955e87dfcfa64cb2b46ccf1025090
|
3 |
size 330143034
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8717e6db6dad3bdb0d92afa70b8fbe0c4677a2360eab813a627812a62061fd4
|
3 |
size 15984
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6c7dfa9863eadd74540b95922e8cee67d3b691b168a951cb8b3349087d7a629
|
3 |
size 15984
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7596c043bb61ec6ab94f537047f856762fd577107f970ea392238fff0ea6ef1
|
3 |
size 15984
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:712dd66678ab2f0cf679625d414555daee92b448e39ad2db26b98722c1b424fc
|
3 |
size 15984
|
last-checkpoint/rng_state_4.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bb08d77b3a8f33a22badf4599bdece3856ac2be5b489c3048c3951f5a13e4fd
|
3 |
size 15984
|
last-checkpoint/rng_state_5.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d84262c7d232955fd6ce9f416c4b38411017050149a8346d4ddba5d641d0b78f
|
3 |
size 15984
|
last-checkpoint/rng_state_6.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:144141c670561050eb2f8450fb88edb4facad52016564e94dfc875ba7b564975
|
3 |
size 15984
|
last-checkpoint/rng_state_7.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbe39dd1e728e6b0298971fe77b09b4d43dbe6b288ac55d64a2318e60f21229e
|
3 |
size 15984
|
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 sha256:416b2ea21de930aef02b3dd806b882963de9b98a0a8d9ff11b933cd6bf4116bc
|
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": 20,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -11,9 +11,9 @@
|
|
11 |
{
|
12 |
"epoch": 0.001183431952662722,
|
13 |
"eval_loss": 3.7497785091400146,
|
14 |
-
"eval_runtime": 2.
|
15 |
-
"eval_samples_per_second":
|
16 |
-
"eval_steps_per_second":
|
17 |
"step": 1
|
18 |
},
|
19 |
{
|
@@ -33,9 +33,9 @@
|
|
33 |
{
|
34 |
"epoch": 0.023668639053254437,
|
35 |
"eval_loss": 3.752192735671997,
|
36 |
-
"eval_runtime": 2.
|
37 |
-
"eval_samples_per_second":
|
38 |
-
"eval_steps_per_second": 37.
|
39 |
"step": 20
|
40 |
},
|
41 |
{
|
@@ -55,9 +55,9 @@
|
|
55 |
{
|
56 |
"epoch": 0.047337278106508875,
|
57 |
"eval_loss": 3.750141143798828,
|
58 |
-
"eval_runtime": 2.
|
59 |
-
"eval_samples_per_second":
|
60 |
-
"eval_steps_per_second":
|
61 |
"step": 40
|
62 |
},
|
63 |
{
|
@@ -77,9 +77,9 @@
|
|
77 |
{
|
78 |
"epoch": 0.07100591715976332,
|
79 |
"eval_loss": 3.730466842651367,
|
80 |
-
"eval_runtime": 2.
|
81 |
-
"eval_samples_per_second":
|
82 |
-
"eval_steps_per_second": 37.
|
83 |
"step": 60
|
84 |
},
|
85 |
{
|
@@ -99,10 +99,54 @@
|
|
99 |
{
|
100 |
"epoch": 0.09467455621301775,
|
101 |
"eval_loss": 3.7425360679626465,
|
102 |
-
"eval_runtime":
|
103 |
-
"eval_samples_per_second":
|
104 |
-
"eval_steps_per_second":
|
105 |
"step": 80
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
106 |
}
|
107 |
],
|
108 |
"logging_steps": 10,
|
@@ -122,7 +166,7 @@
|
|
122 |
"attributes": {}
|
123 |
}
|
124 |
},
|
125 |
-
"total_flos":
|
126 |
"train_batch_size": 2,
|
127 |
"trial_name": null,
|
128 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.14201183431952663,
|
5 |
"eval_steps": 20,
|
6 |
+
"global_step": 120,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
11 |
{
|
12 |
"epoch": 0.001183431952662722,
|
13 |
"eval_loss": 3.7497785091400146,
|
14 |
+
"eval_runtime": 2.5725,
|
15 |
+
"eval_samples_per_second": 583.871,
|
16 |
+
"eval_steps_per_second": 36.541,
|
17 |
"step": 1
|
18 |
},
|
19 |
{
|
|
|
33 |
{
|
34 |
"epoch": 0.023668639053254437,
|
35 |
"eval_loss": 3.752192735671997,
|
36 |
+
"eval_runtime": 2.475,
|
37 |
+
"eval_samples_per_second": 606.872,
|
38 |
+
"eval_steps_per_second": 37.98,
|
39 |
"step": 20
|
40 |
},
|
41 |
{
|
|
|
55 |
{
|
56 |
"epoch": 0.047337278106508875,
|
57 |
"eval_loss": 3.750141143798828,
|
58 |
+
"eval_runtime": 2.4397,
|
59 |
+
"eval_samples_per_second": 615.651,
|
60 |
+
"eval_steps_per_second": 38.529,
|
61 |
"step": 40
|
62 |
},
|
63 |
{
|
|
|
77 |
{
|
78 |
"epoch": 0.07100591715976332,
|
79 |
"eval_loss": 3.730466842651367,
|
80 |
+
"eval_runtime": 2.5074,
|
81 |
+
"eval_samples_per_second": 599.033,
|
82 |
+
"eval_steps_per_second": 37.489,
|
83 |
"step": 60
|
84 |
},
|
85 |
{
|
|
|
99 |
{
|
100 |
"epoch": 0.09467455621301775,
|
101 |
"eval_loss": 3.7425360679626465,
|
102 |
+
"eval_runtime": 2.4554,
|
103 |
+
"eval_samples_per_second": 611.71,
|
104 |
+
"eval_steps_per_second": 38.283,
|
105 |
"step": 80
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.10650887573964497,
|
109 |
+
"grad_norm": Infinity,
|
110 |
+
"learning_rate": 0.000144,
|
111 |
+
"loss": 3.446,
|
112 |
+
"step": 90
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 0.11834319526627218,
|
116 |
+
"grad_norm": Infinity,
|
117 |
+
"learning_rate": 0.00016,
|
118 |
+
"loss": 3.9408,
|
119 |
+
"step": 100
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 0.11834319526627218,
|
123 |
+
"eval_loss": 3.747370719909668,
|
124 |
+
"eval_runtime": 2.528,
|
125 |
+
"eval_samples_per_second": 594.151,
|
126 |
+
"eval_steps_per_second": 37.184,
|
127 |
+
"step": 100
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 0.1301775147928994,
|
131 |
+
"grad_norm": Infinity,
|
132 |
+
"learning_rate": 0.00017600000000000002,
|
133 |
+
"loss": 3.4239,
|
134 |
+
"step": 110
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.14201183431952663,
|
138 |
+
"grad_norm": Infinity,
|
139 |
+
"learning_rate": 0.000192,
|
140 |
+
"loss": 3.7869,
|
141 |
+
"step": 120
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.14201183431952663,
|
145 |
+
"eval_loss": 3.740018606185913,
|
146 |
+
"eval_runtime": 2.5424,
|
147 |
+
"eval_samples_per_second": 590.789,
|
148 |
+
"eval_steps_per_second": 36.973,
|
149 |
+
"step": 120
|
150 |
}
|
151 |
],
|
152 |
"logging_steps": 10,
|
|
|
166 |
"attributes": {}
|
167 |
}
|
168 |
},
|
169 |
+
"total_flos": 3255474413633536.0,
|
170 |
"train_batch_size": 2,
|
171 |
"trial_name": null,
|
172 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:930e523ba424e07364b1eb3e1b298d7c7f59473e3b137fdf485803d46fe2b072
|
3 |
size 6712
|