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:fc51da7795052f16a3b625fd2a129bdc6e43bbd2252ef313486c3652f408894d
+oid sha256:8e3913117ecf7d763340e0e4cd001302ef22e379e06e3ef45a21aea18a044c69
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2825402b4db5042b97f419c54cd8a536a5b42edda643b2cca4af6979a4f47efc
+oid sha256:8b5c802ce1ae82e083a8a02e8420c8b6905c9fcf39f2c1be61e6cf235219db14
 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 sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004716054234623698,
+  "epoch": 0.007074081351935547,
   "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": 10.985,
       "eval_steps_per_second": 10.985,
       "step": 6
+    },
+    {
+      "epoch": 0.005502063273727648,
+      "grad_norm": 14.074959754943848,
+      "learning_rate": 0.0001,
+      "loss": 17.4521,
+      "step": 7
+    },
+    {
+      "epoch": 0.006288072312831598,
+      "grad_norm": 16.047016143798828,
+      "learning_rate": 0.00012,
+      "loss": 17.0565,
+      "step": 8
+    },
+    {
+      "epoch": 0.007074081351935547,
+      "grad_norm": 20.59668731689453,
+      "learning_rate": 0.00014,
+      "loss": 15.4486,
+      "step": 9
+    },
+    {
+      "epoch": 0.007074081351935547,
+      "eval_loss": 15.391473770141602,
+      "eval_runtime": 24.3734,
+      "eval_samples_per_second": 10.996,
+      "eval_steps_per_second": 10.996,
+      "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