Training in progress, epoch 1, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6fd84021b557de987b9e10c20c204e43f1aae37a253103192e8412b912c4ecd
+oid sha256:d10669db550ad84a468c665ddc1bb030f46dc9ad1e3a6e0b0bf309ede8df377a
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b33cbb95d9a4ec2253a3c7845843419073da60d39d06dd8fa25d7524d01bf57f
+oid sha256:c328538702db9167195561c55f853a4d304f1acc123c40740508a0734f03b7c5
 size 107046

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aa86072d894b06ed15a781ebf27303cfbb0a54143c21949f75c3251dd2ec55c
+oid sha256:b97e51ea9f5d34aebc6d066d7c2fb7a20dbec78f27d117049f04bf79c02536c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c657fc64696a443ef7d849612a21fa207361a68fdb8f46c2e175bd76beea6cd
+oid sha256:4576d342b9b65067353ef0684a8e7c0a7953eca1e7c80a1cf34beed923c936d0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9979035639412998,
+  "epoch": 1.9958071278825997,
   "eval_steps": 500,
-  "global_step": 119,
+  "global_step": 238,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -29,6 +29,28 @@
       "eval_samples_per_second": 242.533,
       "eval_steps_per_second": 62.434,
       "step": 119
+    },
+    {
+      "epoch": 1.2578616352201257,
+      "grad_norm": 0.028496425598859787,
+      "learning_rate": 0.00014730878186968837,
+      "loss": 12.1057,
+      "step": 150
+    },
+    {
+      "epoch": 1.6771488469601676,
+      "grad_norm": 0.027717996388673782,
+      "learning_rate": 0.00011189801699716715,
+      "loss": 11.9206,
+      "step": 200
+    },
+    {
+      "epoch": 1.9958071278825997,
+      "eval_loss": 11.916767120361328,
+      "eval_runtime": 0.4141,
+      "eval_samples_per_second": 243.91,
+      "eval_steps_per_second": 62.789,
+      "step": 238
     }
   ],
   "logging_steps": 50,
@@ -48,7 +70,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 134180413440.0,
+  "total_flos": 268360826880.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null