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:d37433f760c9217ba34568916d8a7cc4401facef6ed6a8da76abff1971b18572
+oid sha256:00f8c8a4dfc7501c78f940e1623b753ec818312c1e5b329d4d7fd46bd347fd35
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:468c35a3a5f83c281b144bd28c072af6412ca7b024063d05cd42f535ea0d60a8
+oid sha256:a492359c7e02acd1fadec6b6d551d077c5b5b138be9771858ce3ff42174b3a1e
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28fc964478813f24a3f5bfb214625fd6c3a9f462286b52f0936de8a4d495d883
+oid sha256:e6abadd3ab8536cf571a5393413839497cc66a3d7dd83504f5811cab9d66ff2c
 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": 0.0022656471254602095,
+  "epoch": 0.0033984706881903144,
   "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": 15.746,
       "eval_steps_per_second": 7.873,
       "step": 6
+    },
+    {
+      "epoch": 0.0026432549797035776,
+      "grad_norm": 0.4921773374080658,
+      "learning_rate": 0.00014,
+      "loss": 0.1793,
+      "step": 7
+    },
+    {
+      "epoch": 0.0030208628339469462,
+      "grad_norm": 1.6434965133666992,
+      "learning_rate": 0.00016,
+      "loss": 0.3853,
+      "step": 8
+    },
+    {
+      "epoch": 0.0033984706881903144,
+      "grad_norm": 0.5646060705184937,
+      "learning_rate": 0.00018,
+      "loss": 0.1635,
+      "step": 9
+    },
+    {
+      "epoch": 0.0033984706881903144,
+      "eval_loss": 0.16544446349143982,
+      "eval_runtime": 70.878,
+      "eval_samples_per_second": 15.745,
+      "eval_steps_per_second": 7.873,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2245532414115840.0,
+  "total_flos": 3392187263877120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null