Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d98d4f29d81c1c3ca32c085ae0b3bf6f96cfd37e34a375a0ad66f2ba42199ab
+oid sha256:a0c2b5b64f8fff486f81432d7d08c4858e8c4aa5eb14938efab14b2dcf15b5cb
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:948d1a2b023cfa6b65e34c9746ce2603d1e288812b3605e14741b574016b1e94
+oid sha256:b2ab81eb57e014c058faeef8c19d5679aa4b2cbe8861792fa8e2b7b8264658db
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:289733692b08074dec0b283d1382287b84329d63bfd23cc3ebcac9ebd7041565
+oid sha256:00985fb7e13fdc811c91a3bd76996817a61857ebcea9547c13e16980b6a4ce57
 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": 0.00023284016492845016,
+  "epoch": 0.00034926024739267525,
   "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": 11.075,
       "eval_steps_per_second": 11.075,
       "step": 6
+    },
+    {
+      "epoch": 0.00027164685908319185,
+      "grad_norm": 0.8257654905319214,
+      "learning_rate": 0.00014,
+      "loss": 1.1723,
+      "step": 7
+    },
+    {
+      "epoch": 0.0003104535532379335,
+      "grad_norm": 0.8499470353126526,
+      "learning_rate": 0.00016,
+      "loss": 1.1895,
+      "step": 8
+    },
+    {
+      "epoch": 0.00034926024739267525,
+      "grad_norm": 1.2237374782562256,
+      "learning_rate": 0.00018,
+      "loss": 1.2761,
+      "step": 9
+    },
+    {
+      "epoch": 0.00034926024739267525,
+      "eval_loss": 1.176152229309082,
+      "eval_runtime": 490.047,
+      "eval_samples_per_second": 11.072,
+      "eval_steps_per_second": 11.072,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 783761302093824.0,
+  "total_flos": 1175641953140736.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null