Training in progress, step 1100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df001d6c482b5ebcda095e7d8747a1865cc0830115cc6cd22215f7b4b6077fc1
+oid sha256:828d4a90a79926476ae1bc4aa6d764727385375199b4b2038fbb746b89774971
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3912871294c8600ae8d6a8870fe77e62cd01ff31a2643c7d0d3ace9214d8468c
+oid sha256:9bd31f6a42e09c33577d0850b11db6765f299aa35c2fdf36ab9191122e21e7d5
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93ce7850ba616cb9173c824a87886d7161290c269141086c616c96978133223b
+oid sha256:2479d85779f408734c43086390c11d46c003cabf0a9fda602c9204c5d6de6353
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
+oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.266547441482544,
-  "best_model_checkpoint": "./outputs/checkpoint-1000",
-  "epoch": 1.3333333333333333,
+  "best_metric": 1.2609761953353882,
+  "best_model_checkpoint": "./outputs/checkpoint-1100",
+  "epoch": 1.4666666666666668,
   "eval_steps": 100,
-  "global_step": 1000,
+  "global_step": 1100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,20 @@
       "eval_samples_per_second": 15.263,
       "eval_steps_per_second": 1.914,
       "step": 1000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0002,
+      "loss": 1.0885,
+      "step": 1100
+    },
+    {
+      "epoch": 1.47,
+      "eval_loss": 1.2609761953353882,
+      "eval_runtime": 126.7802,
+      "eval_samples_per_second": 15.223,
+      "eval_steps_per_second": 1.909,
+      "step": 1100
     }
   ],
   "logging_steps": 100,
@@ -154,7 +168,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.545352531420365e+16,
+  "total_flos": 3.899783473241702e+16,
   "trial_name": null,
   "trial_params": null
 }