Training in progress, step 6000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +57 -3
- pytorch_model.bin +1 -1
- runs/May24_08-16-03_555aebd6415b/events.out.tfevents.1684916185.555aebd6415b.20495.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1987250795
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dc14a418d59224cba58e564b6d6eef9aa9100a97c4b5e0ac5c3cbc885eaf925
|
3 |
size 1987250795
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 996026489
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcb324ae10c9946ff9ef4af6f63f22b2dd06013b12fa4e88d3618c532cbf3f06
|
3 |
size 996026489
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8236b1efeea9a0cb188d1516c456991f957b0cd275f7723797fadddb72ce7a7a
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ca778e3dad5cb50f422990d67ea86870f277935e7ee0e0941e09a709f60546d
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92153a01a9bc6795849b819ba557c141c4265ba3ff9cfeb2e9038a64ec17c505
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -60,11 +60,65 @@
|
|
60 |
"eval_samples_per_second": 3.668,
|
61 |
"eval_steps_per_second": 0.237,
|
62 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
}
|
64 |
],
|
65 |
"max_steps": 6000,
|
66 |
"num_train_epochs": 300,
|
67 |
-
"total_flos":
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|
70 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 300.0,
|
5 |
+
"global_step": 6000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
60 |
"eval_samples_per_second": 3.668,
|
61 |
"eval_steps_per_second": 0.237,
|
62 |
"step": 3000
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 200.0,
|
66 |
+
"learning_rate": 2.50625e-05,
|
67 |
+
"loss": 0.0086,
|
68 |
+
"step": 4000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 200.0,
|
72 |
+
"eval_bleu": 95.5885,
|
73 |
+
"eval_em": 0.5803,
|
74 |
+
"eval_gen_len": 80.6978,
|
75 |
+
"eval_loss": 0.40772923827171326,
|
76 |
+
"eval_rm": 0.6283,
|
77 |
+
"eval_runtime": 118.0147,
|
78 |
+
"eval_samples_per_second": 3.533,
|
79 |
+
"eval_steps_per_second": 0.229,
|
80 |
+
"step": 4000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 250.0,
|
84 |
+
"learning_rate": 1.2562499999999999e-05,
|
85 |
+
"loss": 0.0051,
|
86 |
+
"step": 5000
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 250.0,
|
90 |
+
"eval_bleu": 95.5923,
|
91 |
+
"eval_em": 0.6019,
|
92 |
+
"eval_gen_len": 80.6523,
|
93 |
+
"eval_loss": 0.41692906618118286,
|
94 |
+
"eval_rm": 0.6523,
|
95 |
+
"eval_runtime": 120.2437,
|
96 |
+
"eval_samples_per_second": 3.468,
|
97 |
+
"eval_steps_per_second": 0.225,
|
98 |
+
"step": 5000
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 300.0,
|
102 |
+
"learning_rate": 6.250000000000001e-08,
|
103 |
+
"loss": 0.0038,
|
104 |
+
"step": 6000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 300.0,
|
108 |
+
"eval_bleu": 95.481,
|
109 |
+
"eval_em": 0.6019,
|
110 |
+
"eval_gen_len": 80.4676,
|
111 |
+
"eval_loss": 0.42530182003974915,
|
112 |
+
"eval_rm": 0.6547,
|
113 |
+
"eval_runtime": 133.449,
|
114 |
+
"eval_samples_per_second": 3.125,
|
115 |
+
"eval_steps_per_second": 0.202,
|
116 |
+
"step": 6000
|
117 |
}
|
118 |
],
|
119 |
"max_steps": 6000,
|
120 |
"num_train_epochs": 300,
|
121 |
+
"total_flos": 1.014399554069376e+16,
|
122 |
"trial_name": null,
|
123 |
"trial_params": null
|
124 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 996026489
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcb324ae10c9946ff9ef4af6f63f22b2dd06013b12fa4e88d3618c532cbf3f06
|
3 |
size 996026489
|
runs/May24_08-16-03_555aebd6415b/events.out.tfevents.1684916185.555aebd6415b.20495.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2a18636c33728d779873fe4ff60ce1d282acf6f14be5b3378c3077e3bc8ff02
|
3 |
+
size 12278
|