Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc896d9a31fec3347a78d31be4fe1f49ec14e369415b658503f001b1d84fe338
+oid sha256:a0b2b6a37f68a11b4f33f5a8d24f4d13ad60306376de9562a934051a026e48e4
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a96c0758b611fa4347bbfb780c5819105b2f37539ea6bd069a25f799125a5e12
+oid sha256:ccfc3b592f19525a7f25f6a68dcfd22a73155cc759fb742fcf2bde0a33d0871c
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54fbaba1ddfebd4b89dec166b252d6079eab8ffb812f4b0f72ec2d9a57e46917
+oid sha256:e0b94d1122471aca26c892d9b2d4a4e37ccc99bccd12a642f92316f84a6a18ef
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
+oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2179733514785767,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.26666666666666666,
+  "best_metric": 1.202022671699524,
+  "best_model_checkpoint": "./outputs/checkpoint-300",
+  "epoch": 0.4,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,20 @@
       "eval_samples_per_second": 10.863,
       "eval_steps_per_second": 1.362,
       "step": 200
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002,
+      "loss": 1.0046,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.202022671699524,
+      "eval_runtime": 178.5482,
+      "eval_samples_per_second": 10.809,
+      "eval_steps_per_second": 1.355,
+      "step": 300
     }
   ],
   "logging_steps": 100,
@@ -42,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.492559003271168e+16,
+  "total_flos": 2.242334722424832e+16,
   "trial_name": null,
   "trial_params": null
 }