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:e14d57f2d490a8837fbad575e59a9da925fe2ffd03d856285cc37b63b1857ed3
+oid sha256:9522bfbc463bfea6656ead15a83dc446d1c456cf0a1cc34433fb1358ddde439b
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b9e2d810bd320440a7c9c5d5ba45c127cac69c1bbffccb96739a1056abc09ce
+oid sha256:370feb945c14b464d6c59f139b7280b52191460a6e98b4c47c932e7918f71c56
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38317d9b4ba1d8230a1c030d4aee76cbfde777aa0bbebcd78f435b10a1392915
+oid sha256:3cdf2e72b02826124ca59f8c820f38649bf8b862d21d1b6a4a97177560c2e1d6
 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": 0.013029315960912053,
+  "epoch": 0.026058631921824105,
   "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": 5.736,
       "eval_steps_per_second": 2.897,
       "step": 3
+    },
+    {
+      "epoch": 0.01737242128121607,
+      "grad_norm": 0.7923864722251892,
+      "learning_rate": 8e-05,
+      "loss": 3.549,
+      "step": 4
+    },
+    {
+      "epoch": 0.021715526601520086,
+      "grad_norm": 0.9735816121101379,
+      "learning_rate": 0.0001,
+      "loss": 3.4902,
+      "step": 5
+    },
+    {
+      "epoch": 0.026058631921824105,
+      "grad_norm": 1.5655157566070557,
+      "learning_rate": 0.00012,
+      "loss": 3.403,
+      "step": 6
+    },
+    {
+      "epoch": 0.026058631921824105,
+      "eval_loss": 0.910624623298645,
+      "eval_runtime": 17.0593,
+      "eval_samples_per_second": 5.686,
+      "eval_steps_per_second": 2.872,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1820567399301120.0,
+  "total_flos": 3720289902919680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null