Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c925f50ed7de50eeb7b5c2532d551a568884c65aec23dee0552d0fbde5a0c4e
+oid sha256:94a67b901505e7180109f15afdca71a0c4a9d599184f1aecd8801260026e265a
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98f4a9ccaf279d36776b2208e0aabe119b38951dbeac2e8cdd59a85e8810f1fe
+oid sha256:d77480df1dc28e0a6a974aa2fc384018e48fbb0adfb59fc7dba53eb51f2757ab
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:248b83e156267aeaad0b24a8a39efe5d8e1a4161145b352741eb9e33a27f29d7
+oid sha256:37a1d57dcf6d6a809cbd33f03ec44415e52213e48cac682f33531386d9556ac5
 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": 0.02416918429003021,
+  "epoch": 0.03625377643504532,
   "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": 68.075,
       "eval_steps_per_second": 34.361,
       "step": 6
+    },
+    {
+      "epoch": 0.028197381671701913,
+      "grad_norm": 16.026578903198242,
+      "learning_rate": 0.00014,
+      "loss": 13.141,
+      "step": 7
+    },
+    {
+      "epoch": 0.032225579053373615,
+      "grad_norm": 12.509324073791504,
+      "learning_rate": 0.00016,
+      "loss": 12.7861,
+      "step": 8
+    },
+    {
+      "epoch": 0.03625377643504532,
+      "grad_norm": 13.980443954467773,
+      "learning_rate": 0.00018,
+      "loss": 12.8322,
+      "step": 9
+    },
+    {
+      "epoch": 0.03625377643504532,
+      "eval_loss": 2.8865890502929688,
+      "eval_runtime": 1.4984,
+      "eval_samples_per_second": 70.077,
+      "eval_steps_per_second": 35.372,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 45041791795200.0,
+  "total_flos": 67562687692800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null