Training in progress, step 3000
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 +25 -5
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- 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 838981
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ceeb9c4b2fc66056c0ef46757f0f33d554d30f7e0c9528a81b5e4c96974c1b10
|
3 |
size 838981
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242014297
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d103ad46009f8934f120956dc89efb5c547ef690729cfa8fdedca333a6eb1286
|
3 |
size 242014297
|
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 sha256:46e8ea99180f64336e3c9ee277617a470fc3ab9f867509603dd9101cdaaf4f29
|
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:e4fb5513324cb7af4adc926bfce7cbfaa6998837bef58cc3542ea3b6594283ad
|
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 sha256:4c87425c169975acef42a6cd137204ef2ac5b636056155eafc97d710301d2b0c
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "results/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -106,11 +106,31 @@
|
|
106 |
"eval_samples_per_second": 36.018,
|
107 |
"eval_steps_per_second": 1.801,
|
108 |
"step": 2500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
109 |
}
|
110 |
],
|
111 |
"max_steps": 15000,
|
112 |
"num_train_epochs": 3,
|
113 |
-
"total_flos":
|
114 |
"trial_name": null,
|
115 |
"trial_params": null
|
116 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.5638093330791257,
|
3 |
+
"best_model_checkpoint": "results/checkpoint-3000",
|
4 |
+
"epoch": 0.6,
|
5 |
+
"global_step": 3000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
106 |
"eval_samples_per_second": 36.018,
|
107 |
"eval_steps_per_second": 1.801,
|
108 |
"step": 2500
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.6,
|
112 |
+
"learning_rate": 8.424561403508773e-05,
|
113 |
+
"loss": 0.7059,
|
114 |
+
"step": 3000
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.6,
|
118 |
+
"eval_bleu": 0.12580027258921145,
|
119 |
+
"eval_exact_match": 0.152,
|
120 |
+
"eval_loss": 0.835323691368103,
|
121 |
+
"eval_rouge1": 0.5638093330791257,
|
122 |
+
"eval_rouge2": 0.38806045055829985,
|
123 |
+
"eval_rougeL": 0.5445258094241635,
|
124 |
+
"eval_rougeLsum": 0.5516261383865033,
|
125 |
+
"eval_runtime": 55.957,
|
126 |
+
"eval_samples_per_second": 35.742,
|
127 |
+
"eval_steps_per_second": 1.787,
|
128 |
+
"step": 3000
|
129 |
}
|
130 |
],
|
131 |
"max_steps": 15000,
|
132 |
"num_train_epochs": 3,
|
133 |
+
"total_flos": 8076215369072640.0,
|
134 |
"trial_name": null,
|
135 |
"trial_params": null
|
136 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3707
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:decc571ddd8ca581d7ca20dea7d464129d206dc2023a7d7d2fdea2bb30901884
|
3 |
size 3707
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242014297
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d103ad46009f8934f120956dc89efb5c547ef690729cfa8fdedca333a6eb1286
|
3 |
size 242014297
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3707
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:decc571ddd8ca581d7ca20dea7d464129d206dc2023a7d7d2fdea2bb30901884
|
3 |
size 3707
|