Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36d785dc9f57dbb0fd5b895bbd1011197fd62f45ebb01ddde0b5ecf09b383476
+oid sha256:3bc22144321c83e08e00d7c7f277fabaef6484cb15fe784bcb798bd4a44254ae
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7faa0969227a7d6e13277f269736a424418b7fae9686bfaa187d7b65cc9022e
+oid sha256:7f0979dcf4444efdc26623b0c403f5cc6fc6247e9699fed7a3b409f8e9d926a0
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7b14d0c915e2c4063f110f3dbec036a026b529b8820509b2913f154771be18b
+oid sha256:e9ed9626ba6e412f40126198b85320c11d70caab3bee87c19069e3aea6dd4f83
 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": 0.027428571428571427,
+  "epoch": 0.04114285714285714,
   "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": 17.89,
       "eval_steps_per_second": 9.041,
       "step": 6
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.7520653605461121,
+      "learning_rate": 0.00014,
+      "loss": 2.9988,
+      "step": 7
+    },
+    {
+      "epoch": 0.036571428571428574,
+      "grad_norm": 0.684337317943573,
+      "learning_rate": 0.00016,
+      "loss": 2.7895,
+      "step": 8
+    },
+    {
+      "epoch": 0.04114285714285714,
+      "grad_norm": 0.7094518542289734,
+      "learning_rate": 0.00018,
+      "loss": 2.9869,
+      "step": 9
+    },
+    {
+      "epoch": 0.04114285714285714,
+      "eval_loss": 2.6812946796417236,
+      "eval_runtime": 5.1981,
+      "eval_samples_per_second": 17.891,
+      "eval_steps_per_second": 9.042,
+      "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