Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:809efeca0bab9651d4577603ce827c3d0242b62f1646bedae2603fb085d1cb0e
+oid sha256:2b20df6006659935a840452ec0e090385a969f1023469d6141122616aff225b4
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d0fa0c2f8fab8a7912eeb9aae1022fe10a72a71fb8d177dd80bba2a7037a410
+oid sha256:a053843b22f1934427a7723dc598e7a8c9b2866892e934b35762c19d74cb0ff1
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9496d8ed5195cd973b66d4c34811d290189626269b2a31dc82c82d975038725b
+oid sha256:0bd0c719b07becd12707f516b5805a0c5e7f44255f91a52de0c74a2609cd57ec
 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": 0.0005157408402277856,
+  "epoch": 0.0007736112603416783,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,35 @@
       "eval_samples_per_second": 31.104,
       "eval_steps_per_second": 15.555,
       "step": 6
+    },
+    {
+      "epoch": 0.0006016976469324165,
+      "grad_norm": 18.490615844726562,
+      "learning_rate": 0.00014,
+      "loss": 14.4872,
+      "step": 7
+    },
+    {
+      "epoch": 0.0006876544536370474,
+      "grad_norm": 22.34310531616211,
+      "learning_rate": 0.00016,
+      "loss": 14.1407,
+      "step": 8
+    },
+    {
+      "epoch": 0.0007736112603416783,
+      "grad_norm": 17.5768985748291,
+      "learning_rate": 0.00018,
+      "loss": 11.6362,
+      "step": 9
+    },
+    {
+      "epoch": 0.0007736112603416783,
+      "eval_loss": 2.661543130874634,
+      "eval_runtime": 149.1061,
+      "eval_samples_per_second": 32.856,
+      "eval_steps_per_second": 16.431,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -84,7 +113,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 179259385577472.0,
+  "total_flos": 268889078366208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null