Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ce7ffbf41919a09cb7f41ecfc691d2777eeea4759dea90abcc883b1c2ca7cdc
+oid sha256:92c6adf8f4340fa05c4cff561b05ac7aa6717ed5aad94be8bc13ae5db386177f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:387f7310bd0c74de2c53e93c66957511b8f4b9a57baba58e1d75956a19a21adf
+oid sha256:55b354e2c22ea89e6399c1e15f99a845b4c91668f457d64756465efbbd682d2e
 size 43122580

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4efb600f1c3500add79f72139e980a8df1a4b60b899741720596608757ec0b80
+oid sha256:ef12b6dfbbd8e9ffb3ee559ac88ba28ccd4ecbca575ae9e6bba9374f75ce34ca
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2c328ca304e4a83b705e1c382163cbaf9cdf3f6a2a09f6efddc567c79906d4b
+oid sha256:6771eaea8d119793794214c4189a1e1af4912c9df24e2598e943f186f276b24a
 size 14512

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": 0.006191950464396285,
+  "epoch": 0.009287925696594427,
   "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": 63.718,
       "eval_steps_per_second": 15.988,
       "step": 6
+    },
+    {
+      "epoch": 0.007223942208462332,
+      "grad_norm": 11.56080150604248,
+      "learning_rate": 0.00014,
+      "loss": 7.9041,
+      "step": 7
+    },
+    {
+      "epoch": 0.008255933952528379,
+      "grad_norm": 11.11003303527832,
+      "learning_rate": 0.00016,
+      "loss": 7.3022,
+      "step": 8
+    },
+    {
+      "epoch": 0.009287925696594427,
+      "grad_norm": 12.207099914550781,
+      "learning_rate": 0.00018,
+      "loss": 5.3686,
+      "step": 9
+    },
+    {
+      "epoch": 0.009287925696594427,
+      "eval_loss": 4.850965976715088,
+      "eval_runtime": 12.8178,
+      "eval_samples_per_second": 63.739,
+      "eval_steps_per_second": 15.993,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2219477097775104.0,
+  "total_flos": 3329215646662656.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null