Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fe78fb87e7a8fdbce25f80598e2db128c962a6416037e613b49940f72cef06f
+oid sha256:6f994a4018fa71c94fbdc2c5d53cefe31e9b57daebcacd4522bf0fe082019199
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb451445005f97897bd0d3cb1f15123a8b29e74018cb057da215f5ac75dcfa42
+oid sha256:e23ea3985ab49df9ce1eaeacd07a7e7ca7f261d7b5d614a6a0b3fe80429652ae
 size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f6dac5cbce9db8817c3f5bc9eaba71a1796910a90d3fdf54f55d4a6a5b455fd
+oid sha256:c587c90db37dd17929ca520ca809393eec3527e02b375ea20b5c0f12fbd18ecb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
+oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021729289271163424,
+  "epoch": 0.032593933906745136,
   "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": 14.157,
       "eval_steps_per_second": 7.094,
       "step": 6
+    },
+    {
+      "epoch": 0.025350837483023993,
+      "grad_norm": 17.764286041259766,
+      "learning_rate": 7e-05,
+      "loss": 9.3632,
+      "step": 7
+    },
+    {
+      "epoch": 0.028972385694884563,
+      "grad_norm": 15.867535591125488,
+      "learning_rate": 8e-05,
+      "loss": 7.6773,
+      "step": 8
+    },
+    {
+      "epoch": 0.032593933906745136,
+      "grad_norm": 16.599441528320312,
+      "learning_rate": 9e-05,
+      "loss": 6.5199,
+      "step": 9
+    },
+    {
+      "epoch": 0.032593933906745136,
+      "eval_loss": NaN,
+      "eval_runtime": 32.8587,
+      "eval_samples_per_second": 14.151,
+      "eval_steps_per_second": 7.091,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9650863589031936.0,
+  "total_flos": 1.4476295383547904e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null