Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:430de1ae2da4dd6a3b2d79c63a2ececa37abfd84ff8e20f02cdc486e4c3cb7d5
+oid sha256:8e543569fec4b549c5cc3018adea2a9d6d91a3a8c22dfa34e2e79b746baeb65f
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:143579abe6990b4550bf6e6cf9ed9c0af463372861d4379fcd9e06223fa5707e
+oid sha256:65282f76c836614e297ecb2c947a5976841cde9c6afe8ec730667e87caf3468f
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe300d7c5ab10b566794c92461448fbc4b1030e2c8290ab8f4cd627fc33f0bc0
+oid sha256:98929920e2becfcab04e82aa93e81382f3a01ef05c01842148a47548a3a1eeff
 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": 0.001014584654407102,
+  "epoch": 0.0015218769816106531,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 29.137,
       "eval_steps_per_second": 14.568,
       "step": 6
+    },
+    {
+      "epoch": 0.0011836820968082857,
+      "grad_norm": 6.458924293518066,
+      "learning_rate": 0.00014,
+      "loss": 5.675,
+      "step": 7
+    },
+    {
+      "epoch": 0.0013527795392094695,
+      "grad_norm": 5.89903450012207,
+      "learning_rate": 0.00016,
+      "loss": 4.7366,
+      "step": 8
+    },
+    {
+      "epoch": 0.0015218769816106531,
+      "grad_norm": 5.359555244445801,
+      "learning_rate": 0.00018,
+      "loss": 4.34,
+      "step": 9
+    },
+    {
+      "epoch": 0.0015218769816106531,
+      "eval_loss": 3.663693904876709,
+      "eval_runtime": 85.4769,
+      "eval_samples_per_second": 29.131,
+      "eval_steps_per_second": 14.565,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 719886967898112.0,
+  "total_flos": 1096970617749504.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null