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:d2f5de76adeaf71c7d168d54d77ea719c319a44fc14181bee407278cae3cd513
+oid sha256:fc652b9b2650947437b8e44bca010f2cac7c776de11d9d283f1edf68add1e327
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6a2e62711828db280ad95476b0a6279b4cec4bf348f642935baf72a6a692e7f
+oid sha256:9e8b18194a4816496b253b74dc697cdf88b8828ef54991cd864e00273bc2b59d
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:568ee55b83fd3bf20664b59f33f857dcb4b212e91aa3990c870da955df7bec07
+oid sha256:8a0953b49b8306e77f06414fcb616dccf1f630251fd7ae56f8b47cec96f1a40e
 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": 0.0005170965031348976,
+  "epoch": 0.0007756447547023463,
   "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": 24.918,
       "eval_steps_per_second": 12.459,
       "step": 6
+    },
+    {
+      "epoch": 0.0006032792536573804,
+      "grad_norm": 1.0203039646148682,
+      "learning_rate": 0.00014,
+      "loss": 1.0586,
+      "step": 7
+    },
+    {
+      "epoch": 0.0006894620041798634,
+      "grad_norm": 1.3906350135803223,
+      "learning_rate": 0.00016,
+      "loss": 1.7009,
+      "step": 8
+    },
+    {
+      "epoch": 0.0007756447547023463,
+      "grad_norm": 2.2116494178771973,
+      "learning_rate": 0.00018,
+      "loss": 2.6583,
+      "step": 9
+    },
+    {
+      "epoch": 0.0007756447547023463,
+      "eval_loss": NaN,
+      "eval_runtime": 196.0011,
+      "eval_samples_per_second": 24.928,
+      "eval_steps_per_second": 12.464,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 676540148613120.0,
+  "total_flos": 1025060831232000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null