Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5370d6e119f82c2281ad3e747ad13e7c2e46b8e62eb754bc042d35e4e5ffa09
+oid sha256:f5273cb63fd23b610eef47eb99e12d17294d83da373346574dd99b78fe77d3a5
 size 81576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:238a3f2ac9d2ca27ddd32a768c933231d6aa867a27283adef9070cc82162a347
+oid sha256:3fb0161f754c2c7db6ced46ac136920dfe4ffd6da3ed7f340117d156e7ccaadf
 size 173094

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
+oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00010597430123195125,
+  "epoch": 0.0002119486024639025,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 405.579,
       "eval_steps_per_second": 202.789,
       "step": 3
+    },
+    {
+      "epoch": 0.00014129906830926835,
+      "grad_norm": 0.23857171833515167,
+      "learning_rate": 8e-05,
+      "loss": 10.8423,
+      "step": 4
+    },
+    {
+      "epoch": 0.00017662383538658542,
+      "grad_norm": 0.15420323610305786,
+      "learning_rate": 0.0001,
+      "loss": 10.8284,
+      "step": 5
+    },
+    {
+      "epoch": 0.0002119486024639025,
+      "grad_norm": 0.15825432538986206,
+      "learning_rate": 0.00012,
+      "loss": 10.8331,
+      "step": 6
+    },
+    {
+      "epoch": 0.0002119486024639025,
+      "eval_loss": 10.839529037475586,
+      "eval_runtime": 29.8094,
+      "eval_samples_per_second": 399.873,
+      "eval_steps_per_second": 199.937,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 246088728576.0,
+  "total_flos": 492177457152.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null