Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f58a9b05205fc3e2da1dc9b9f63c09eca7b2b1a85bd373460bc77d2736fac52
+oid sha256:bdfe5989b601509df4c278de90507f3dce8631542bdd9507b00f6a2e2b76d907
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a504a88443f45ac8a807db28ab8a4242a5cf07801123fb7e52ab53da4b4a7ec
+oid sha256:45a8cef4bf2ad76f7f052e00583e52a9b24c91d99a800fa6f0db193377472165
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85b0ae6c3bd2ac4ea01467a5edbc086cdc303e1ace1b12b41ab97be3e932f8c7
+oid sha256:ab4032206871f76f267774b23b5210fddd18559968f207e84376a2a9e45c5846
 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": 0.021957913998170174,
+  "epoch": 0.03293687099725526,
   "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": 63.342,
       "eval_steps_per_second": 31.947,
       "step": 6
+    },
+    {
+      "epoch": 0.025617566331198535,
+      "grad_norm": 17.392303466796875,
+      "learning_rate": 0.00014,
+      "loss": 4.6108,
+      "step": 7
+    },
+    {
+      "epoch": 0.0292772186642269,
+      "grad_norm": 16.35502815246582,
+      "learning_rate": 0.00016,
+      "loss": 3.6766,
+      "step": 8
+    },
+    {
+      "epoch": 0.03293687099725526,
+      "grad_norm": 14.937495231628418,
+      "learning_rate": 0.00018,
+      "loss": 2.7729,
+      "step": 9
+    },
+    {
+      "epoch": 0.03293687099725526,
+      "eval_loss": 1.7922669649124146,
+      "eval_runtime": 1.7269,
+      "eval_samples_per_second": 66.594,
+      "eval_steps_per_second": 33.586,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 153475186950144.0,
+  "total_flos": 230212780425216.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null