Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37a3a4b2440a0731bb0dfdb0182d215c5e3b2028cc81c495933347972ad3bc85
+oid sha256:af365a018660eaeb234dd89306b2ab35b515d2b1df75be03c4ce1baa5ac37085
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df48676843bf1d3b62189847064a5ec09622c23bf4d0d5d5e3fe361c9dcf2d17
+oid sha256:29e6bddd66bb05ec5f2c7e8a685001574207e728c1802736c3402f736ae721d3
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f9f40d597a7abf41ad3ecf49e11bba5a13f6731550efb96e2fa2f1ae0dfe08
+oid sha256:c4dd2959c43a2400319de9619aa75664f6053b7ca8bf12b1e8d41e00d166b414
 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": 0.026030368763557483,
+  "epoch": 0.039045553145336226,
   "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": 54.361,
       "eval_steps_per_second": 27.461,
       "step": 6
+    },
+    {
+      "epoch": 0.03036876355748373,
+      "grad_norm": 1.9502086639404297,
+      "learning_rate": 0.00014,
+      "loss": 14.3359,
+      "step": 7
+    },
+    {
+      "epoch": 0.03470715835140998,
+      "grad_norm": 2.898710250854492,
+      "learning_rate": 0.00016,
+      "loss": 14.8791,
+      "step": 8
+    },
+    {
+      "epoch": 0.039045553145336226,
+      "grad_norm": 2.074517011642456,
+      "learning_rate": 0.00018,
+      "loss": 15.2378,
+      "step": 9
+    },
+    {
+      "epoch": 0.039045553145336226,
+      "eval_loss": 3.7467966079711914,
+      "eval_runtime": 1.7559,
+      "eval_samples_per_second": 55.243,
+      "eval_steps_per_second": 27.906,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 75069652992000.0,
+  "total_flos": 114481220812800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null