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:ae0f5f651054af1da40d468795a86920400cfb913e020f231831e431a65d08c8
+oid sha256:c2c6d20ac1fc3d2f845040cd7d83e431352418538286fad7f04c2307f66d22b1
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:325dbbecb7713261bcb9217b82b53ff2e419bac294fdd316d994ba745fcd1d1b
+oid sha256:aad33f0f544d110740f60ab77540777854475098d2698c5e6cd53cf652656804
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0eab46050d79b9c31cd62a3e05293e6ffdd1c099e6cb3ff38292e5325a4d0ef
+oid sha256:292c234cb65d6fb97167d7e8a7990ce75ed08617a4275391e22b50c0af4f3a3a
 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": 0.0031189083820662767,
+  "epoch": 0.004678362573099415,
   "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": 76.816,
       "eval_steps_per_second": 38.456,
       "step": 6
+    },
+    {
+      "epoch": 0.0036387264457439896,
+      "grad_norm": 19.44442367553711,
+      "learning_rate": 0.00014,
+      "loss": 7.4614,
+      "step": 7
+    },
+    {
+      "epoch": 0.004158544509421702,
+      "grad_norm": 23.95518684387207,
+      "learning_rate": 0.00016,
+      "loss": 6.9581,
+      "step": 8
+    },
+    {
+      "epoch": 0.004678362573099415,
+      "grad_norm": 21.72780990600586,
+      "learning_rate": 0.00018,
+      "loss": 6.5957,
+      "step": 9
+    },
+    {
+      "epoch": 0.004678362573099415,
+      "eval_loss": 1.6892961263656616,
+      "eval_runtime": 10.5882,
+      "eval_samples_per_second": 76.595,
+      "eval_steps_per_second": 38.345,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 105274278936576.0,
+  "total_flos": 157911418404864.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null