Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86b8bc8cd07a7354e54251b66e2b0361ec7b33d25e05e2e6c5f3eb8196e21674
+oid sha256:d9ccf7e75de435307c7571e66f309f47ce3bc60a24d154e4c29461c451b4aee3
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d856dfdd31b36d9f145d107a21402874caef30f4d995802e004e07847ab703
+oid sha256:652be3e9b98a9a204438ef02a677ef30d899316ffe9f83fcf9373043a30447b1
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d6592a6ee630db08a9825b7a8de69d83be5485d8b50ac75c3b5952c7a9fc409
+oid sha256:32e39b58f8dd1428862d10b2ca179766f5915d74ecb29dc037da3881ece550f5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0011812186238803033,
+  "epoch": 0.0023624372477606065,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 4.59,
       "eval_steps_per_second": 4.59,
       "step": 3
+    },
+    {
+      "epoch": 0.0015749581651737375,
+      "grad_norm": 4.442303657531738,
+      "learning_rate": 8e-05,
+      "loss": 3.3335,
+      "step": 4
+    },
+    {
+      "epoch": 0.001968697706467172,
+      "grad_norm": 2.875202178955078,
+      "learning_rate": 0.0001,
+      "loss": 2.1078,
+      "step": 5
+    },
+    {
+      "epoch": 0.0023624372477606065,
+      "grad_norm": 2.5976645946502686,
+      "learning_rate": 0.00012,
+      "loss": 1.8696,
+      "step": 6
+    },
+    {
+      "epoch": 0.0023624372477606065,
+      "eval_loss": 2.2479214668273926,
+      "eval_runtime": 116.5681,
+      "eval_samples_per_second": 4.59,
+      "eval_steps_per_second": 4.59,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2097116079980544.0,
+  "total_flos": 4194232159961088.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null