Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b71afea65a127d7c26f02f1044eb58dee77e79e330b71fa56563878cd0b0267
+oid sha256:4f0d9ae747d73d46e771dd5be015db65c9e868b05ab212f319ee9d08281eceb2
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8891b1988e5300347c85e1794910d24cd07a1d3a5499d3c820ab92c4a450b6f
+oid sha256:f987e048123dc6f8b7da1a180149daacc0106d753c5a533998e015ffa414dfc2
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc404b94fb6a98c735e540840990b665015acf5acade7920b28911b4dc1556ef
+oid sha256:3e09a8c59c3f41f2c2255af0db63699659ef41692967df867b13af0b15265b56
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
+oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07174887892376682,
+  "epoch": 0.10762331838565023,
   "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": 21.638,
       "eval_steps_per_second": 10.896,
       "step": 6
+    },
+    {
+      "epoch": 0.08370702541106129,
+      "grad_norm": 12.865381240844727,
+      "learning_rate": 7e-05,
+      "loss": 28.8971,
+      "step": 7
+    },
+    {
+      "epoch": 0.09566517189835576,
+      "grad_norm": 14.876195907592773,
+      "learning_rate": 8e-05,
+      "loss": 30.2847,
+      "step": 8
+    },
+    {
+      "epoch": 0.10762331838565023,
+      "grad_norm": 15.215254783630371,
+      "learning_rate": 9e-05,
+      "loss": 26.7162,
+      "step": 9
+    },
+    {
+      "epoch": 0.10762331838565023,
+      "eval_loss": 1.742897391319275,
+      "eval_runtime": 6.4966,
+      "eval_samples_per_second": 21.704,
+      "eval_steps_per_second": 10.929,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7614327410393088.0,
+  "total_flos": 1.140113195139072e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null