Training in progress, step 4962

generation_config.json

@@ -1,7 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "pad_token_id": 3,
-  "transformers_version": "4.31.0"
-}

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4187fa2fcde2182366cb42d84c4cf5de4ac786b1707d83e95ab69962243c76ff
+oid sha256:c718401e44301e7b6b0916484ddf1c5bcc01330ee4727d76b71cf2ed469c5ca7
 size 4473888693

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdfc3439e95dd385b1b4b54f64710e5828fd199ca4b8708b1ba3b02b959e9a50
+oid sha256:777293302c4d76ea91b8cbdaeeeba26e11bd1803a22107140aafa16914330c6c
 size 2236957537

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f59d140cd35a488e94c369977bac2659ceece8330825c3fa76290dfd6251e5c3
+oid sha256:c6369e7a8ae0c3f7b8b98eb916a8737c71a3d74933f972fb7688df71a66b6095
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2870863226105068,
-  "global_step": 2481,
+  "epoch": 0.5741726452210136,
+  "global_step": 4962,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -72,11 +72,83 @@
       "learning_rate": 1.429761629252488e-05,
       "loss": 2.1086,
       "step": 2472
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.382087479750058e-05,
+      "loss": 2.0791,
+      "step": 2678
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.3344133302476279e-05,
+      "loss": 2.0026,
+      "step": 2884
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.2867391807451979e-05,
+      "loss": 1.9953,
+      "step": 3090
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.2390650312427679e-05,
+      "loss": 2.0375,
+      "step": 3296
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.19185373756075e-05,
+      "loss": 2.0465,
+      "step": 3502
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.144411015968526e-05,
+      "loss": 2.0147,
+      "step": 3708
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.096736866466096e-05,
+      "loss": 2.0066,
+      "step": 3914
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.0490627169636659e-05,
+      "loss": 2.0109,
+      "step": 4120
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0013885674612359e-05,
+      "loss": 1.9669,
+      "step": 4326
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.537144179588059e-06,
+      "loss": 1.9822,
+      "step": 4532
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.062716963665819e-06,
+      "loss": 1.9876,
+      "step": 4738
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.585975468641519e-06,
+      "loss": 1.9557,
+      "step": 4944
     }
   ],
   "max_steps": 8642,
   "num_train_epochs": 1,
-  "total_flos": 4608244064452608.0,
+  "total_flos": 9216488128905216.0,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c780d21d141506caddc06c5631ca9da881392ff3082a44f5e4c56b318d78815
-size 4027
+oid sha256:805af7f0ae2c315b9a5aa85e8153519d586ecfae4cf097a3553c416e6588254e
+size 3963

pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ad1047af4d787fcc1458849f4291e7a32cc4ddffeac14bd3fe057f3da7b7c5dd
-size 2236957537