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:de74315dd365dc03d92400edc40b5412ea95c76e183a88259c04976cc965720a
+oid sha256:2215aad23cad14b5f096533ae7ddb6c023bb789cdbc9114f88b32b5d27d7c330
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca561e5df296c0cb0500d617e29915873914b32b92747324440be1e03cb0d8b7
+oid sha256:6804096694a33dbf356cc12deaf53f08737ba844a84edb42ff4788fcfdcc9f73
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6e8ca24aac7e307d010457ce60f69e37da8526188eb56176a7bd24d50bce925
+oid sha256:e3f9f40d597a7abf41ad3ecf49e11bba5a13f6731550efb96e2fa2f1ae0dfe08
 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": 0.013015184381778741,
+  "epoch": 0.026030368763557483,
   "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": 55.15,
       "eval_steps_per_second": 27.859,
       "step": 3
+    },
+    {
+      "epoch": 0.01735357917570499,
+      "grad_norm": 2.909278392791748,
+      "learning_rate": 8e-05,
+      "loss": 15.5635,
+      "step": 4
+    },
+    {
+      "epoch": 0.021691973969631236,
+      "grad_norm": 2.349195957183838,
+      "learning_rate": 0.0001,
+      "loss": 15.3922,
+      "step": 5
+    },
+    {
+      "epoch": 0.026030368763557483,
+      "grad_norm": 1.8822170495986938,
+      "learning_rate": 0.00012,
+      "loss": 15.4836,
+      "step": 6
+    },
+    {
+      "epoch": 0.026030368763557483,
+      "eval_loss": 3.7893669605255127,
+      "eval_runtime": 1.7797,
+      "eval_samples_per_second": 54.503,
+      "eval_steps_per_second": 27.532,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 35658085171200.0,
+  "total_flos": 75069652992000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null