Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9523506355dfecaa8f7931e8bb12311b1a6baa3402232330d70dbea49bd12a6a
+oid sha256:9b9c8339d1c47e0a4bcd66467ba812c91763286283f13bd46213e2d70a3e8e6e
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff3e77d56055bb5b1487fd9cce6fbe73f6f4ae42c7cd239fa78c048f52ece91
+oid sha256:fcf2cc8ca3ef9409067c7f22817433bf0c7778fc6bc90d1151a9ad418be018e1
 size 263088

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbe38599c452d9ae6dc34f6e1fc26d8c070f9321d6d7b5ad8731beaf1827578f
+oid sha256:59d799f504d9e96669c3b322ccf044cf42ed69181feb6c152cba674fa2359f08
 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": 0.028985507246376812,
+  "epoch": 0.043478260869565216,
   "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": 56.513,
       "eval_steps_per_second": 28.256,
       "step": 6
+    },
+    {
+      "epoch": 0.033816425120772944,
+      "grad_norm": 4.814146518707275,
+      "learning_rate": 0.00014,
+      "loss": 44.2293,
+      "step": 7
+    },
+    {
+      "epoch": 0.03864734299516908,
+      "grad_norm": 4.547501087188721,
+      "learning_rate": 0.00016,
+      "loss": 44.1166,
+      "step": 8
+    },
+    {
+      "epoch": 0.043478260869565216,
+      "grad_norm": 4.67207145690918,
+      "learning_rate": 0.00018,
+      "loss": 44.1135,
+      "step": 9
+    },
+    {
+      "epoch": 0.043478260869565216,
+      "eval_loss": 11.005003929138184,
+      "eval_runtime": 1.5478,
+      "eval_samples_per_second": 56.855,
+      "eval_steps_per_second": 28.428,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 499189284864.0,
+  "total_flos": 748783927296.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null