Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d863d7ce5956be31a524ef320393777e3676dfb75bd6c0e7872ff59d874b2e7
+oid sha256:5669fbc557d8c0b6d117b5f0add48fc5188c107e89ff1151689d193fd6886fad
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ca9487c266863aa02a60a4f3f2b7323665c54ad0b2393d6e1a271878fdd0905
+oid sha256:58e5eef3a648bafbe1b2ad82f7f4d8de708b7f0d44ee7bcc2d61ba3b4755afd4
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6844052d85c78c636bdbdeb9a19e74028ffe822c2257112144b10c9d8e82449b
+oid sha256:8fa0cd2311a863a53c7b9c00754d8a568b5bc8a382e272e0f99aa88e8f39b593
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
+oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3373662233352661,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 1.4666666666666668,
+  "best_metric": 1.331199288368225,
+  "best_model_checkpoint": "./outputs/checkpoint-1200",
+  "epoch": 1.6,
   "eval_steps": 100,
-  "global_step": 1100,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -161,6 +161,20 @@
       "eval_samples_per_second": 12.713,
       "eval_steps_per_second": 1.594,
       "step": 1100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 1.0896,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.331199288368225,
+      "eval_runtime": 151.8209,
+      "eval_samples_per_second": 12.712,
+      "eval_steps_per_second": 1.594,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
@@ -168,7 +182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.013163020838912e+16,
+  "total_flos": 7.650403112798208e+16,
   "trial_name": null,
   "trial_params": null
 }