Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d447f517db94f23206d078cf95abd12aa2803f36267f5e6020bfa8b8cea8f2a2
+oid sha256:b6bbb1135715a5375e426410494fdd5898b0f3cd2dbbb328394327544913bc31
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c931e422a6d158507735def8e697ce89b9f4c1a64be522579ce6701325c90bf9
+oid sha256:e78701ceaafa565e841db6004820b0e15eeb265d40f940ada309d1965a3c800a
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a9c01bb08fabdb4105f03cc42a9544dca7c722b687afb8cabdeaf14862f778a
+oid sha256:85b0ae6c3bd2ac4ea01467a5edbc086cdc303e1ace1b12b41ab97be3e932f8c7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.026172300981461286,
+  "epoch": 0.03925845147219193,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,35 @@
       "eval_samples_per_second": 21.902,
       "eval_steps_per_second": 11.064,
       "step": 6
+    },
+    {
+      "epoch": 0.030534351145038167,
+      "grad_norm": 4.009768486022949,
+      "learning_rate": 0.00014,
+      "loss": 3.3925,
+      "step": 7
+    },
+    {
+      "epoch": 0.03489640130861505,
+      "grad_norm": 3.9984865188598633,
+      "learning_rate": 0.00016,
+      "loss": 2.9648,
+      "step": 8
+    },
+    {
+      "epoch": 0.03925845147219193,
+      "grad_norm": 3.600208044052124,
+      "learning_rate": 0.00018,
+      "loss": 2.6364,
+      "step": 9
+    },
+    {
+      "epoch": 0.03925845147219193,
+      "eval_loss": 2.529499053955078,
+      "eval_runtime": 4.0989,
+      "eval_samples_per_second": 23.665,
+      "eval_steps_per_second": 11.954,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -84,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 53422898282496.0,
+  "total_flos": 80134347423744.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null