Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:027b88e75bf42b9fc8468a450e362e3af6ec7956b67f3fb07719aeccceca47a4
+oid sha256:b0437e213488f2d1ceaadabe26b642c36171fce0b2fb7132091b543c3ca71329
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd05b2467efc7f30a226e1bda887159ca225c41bca1ca5c572ad297c32e65871
+oid sha256:4426a17839627b83fc1e77057f2cf41ba8d6f3127d38369eef1834830820cf5b
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f3e0d009e0ec3fd5ee7f335d17337d83548753eb73ecf4cd0160baac45f5971
+oid sha256:c535d322f74c9d3b81f5ae8eda9978ae89ee98f7142986d1695029a6439098ec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
+oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0019447370553439753,
+  "epoch": 0.002917105583015963,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 6.931,
       "eval_steps_per_second": 0.867,
       "step": 18
+    },
+    {
+      "epoch": 0.0022688598979013048,
+      "grad_norm": 0.8526450395584106,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 2.0765,
+      "step": 21
+    },
+    {
+      "epoch": 0.002592982740458634,
+      "grad_norm": 0.7029660940170288,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 2.0004,
+      "step": 24
+    },
+    {
+      "epoch": 0.002917105583015963,
+      "grad_norm": 0.7902804613113403,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.9568,
+      "step": 27
+    },
+    {
+      "epoch": 0.002917105583015963,
+      "eval_loss": 1.9333840608596802,
+      "eval_runtime": 2246.1817,
+      "eval_samples_per_second": 6.94,
+      "eval_steps_per_second": 0.868,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.746463492335206e+16,
+  "total_flos": 7.11969523850281e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null