Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28975e11ad04c5376ff9f4907b79a73df2c48bf08f638b5b5199b828cf04f8d8
+oid sha256:a3ef76f7cfba626d2931c74c23c78b46c203e1c17b7834d3de74536dfed5f95a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10755020aebf8ba4b6be17385c5e26379cd54a20d4bff6d9012642ba44c6a735
+oid sha256:fb8cd74da008f2013b8435f2560306701d052359d1d1e76c966970a0693c79d9
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e96a464897d18d2f2ccf05e846c1054fa66e18da8e69d55ca3b097eaaff40019
+oid sha256:b77ec1d9059fbf29655439de7be3898314e6d6e711dfa2949a49c214c62651ad
 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": 0.013986013986013986,
+  "epoch": 0.027972027972027972,
   "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": 3.976,
       "eval_steps_per_second": 2.01,
       "step": 3
+    },
+    {
+      "epoch": 0.018648018648018648,
+      "grad_norm": 1.8156577348709106,
+      "learning_rate": 8e-05,
+      "loss": 2.4177,
+      "step": 4
+    },
+    {
+      "epoch": 0.023310023310023312,
+      "grad_norm": 1.799171805381775,
+      "learning_rate": 0.0001,
+      "loss": 2.258,
+      "step": 5
+    },
+    {
+      "epoch": 0.027972027972027972,
+      "grad_norm": 1.4947116374969482,
+      "learning_rate": 0.00012,
+      "loss": 1.9516,
+      "step": 6
+    },
+    {
+      "epoch": 0.027972027972027972,
+      "eval_loss": 1.6914260387420654,
+      "eval_runtime": 22.9057,
+      "eval_samples_per_second": 3.973,
+      "eval_steps_per_second": 2.008,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2225661850681344.0,
+  "total_flos": 4451323701362688.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null