Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fa2302be375b9d5f9a388bc5bcc6eed43765e30142e0ef505f5085de1cb8aa0
+oid sha256:fe1a9afd93f5adfc339e8b64839ea9cd1badc6da6cdf955be8603fb8a03aab1b
 size 14293800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9cc8240c4663ef9bf4a7ce28f346a6be2eca39bab05c87f5074295ba639714b
+oid sha256:368852d5287812b078f9615ffc02b84af3192a6907d483e7fcc701d413473f84
 size 7579748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:365824384ac10cb30bec16436ea40f55ca6669bb0dc0a6fb7cea0c684c75923b
+oid sha256:147f86daa998915c5d165d9ceed625464a9087a004ce02c3508f4ce18620367b
 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": 0.0023899621589324837,
+  "epoch": 0.0035849432383987254,
   "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": 70.778,
       "eval_steps_per_second": 35.389,
       "step": 6
+    },
+    {
+      "epoch": 0.0027882891854212307,
+      "grad_norm": 17.844425201416016,
+      "learning_rate": 0.00014,
+      "loss": 28.2968,
+      "step": 7
+    },
+    {
+      "epoch": 0.003186616211909978,
+      "grad_norm": 17.832948684692383,
+      "learning_rate": 0.00016,
+      "loss": 22.4622,
+      "step": 8
+    },
+    {
+      "epoch": 0.0035849432383987254,
+      "grad_norm": 18.43077850341797,
+      "learning_rate": 0.00018,
+      "loss": 24.7027,
+      "step": 9
+    },
+    {
+      "epoch": 0.0035849432383987254,
+      "eval_loss": 5.739309310913086,
+      "eval_runtime": 14.8181,
+      "eval_samples_per_second": 71.399,
+      "eval_steps_per_second": 35.7,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 45257412575232.0,
+  "total_flos": 67886118862848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null