Training in progress, epoch 2, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d10669db550ad84a468c665ddc1bb030f46dc9ad1e3a6e0b0bf309ede8df377a
+oid sha256:aa61242d59dde07b6e124c28e4f02961504a3d80a62d3744879f8d576710c5a1
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c328538702db9167195561c55f853a4d304f1acc123c40740508a0734f03b7c5
+oid sha256:4bff118783a624c3d4494650098c048335a60deb649201045a57196051f28776
 size 107046

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b97e51ea9f5d34aebc6d066d7c2fb7a20dbec78f27d117049f04bf79c02536c3
+oid sha256:f1f6811de7fd6719f9ba6d6a0209af7f4bc36fd4331e413781421b0ce2308264
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4576d342b9b65067353ef0684a8e7c0a7953eca1e7c80a1cf34beed923c936d0
+oid sha256:e3ab4343fd37af80ff3b7a6d2bbb453cb34e903babf826a940b14f4bd54d6552
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9958071278825997,
+  "epoch": 2.9937106918238996,
   "eval_steps": 500,
-  "global_step": 238,
+  "global_step": 357,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -51,6 +51,35 @@
       "eval_samples_per_second": 243.91,
       "eval_steps_per_second": 62.789,
       "step": 238
+    },
+    {
+      "epoch": 2.0964360587002098,
+      "grad_norm": 0.03638681024312973,
+      "learning_rate": 7.64872521246459e-05,
+      "loss": 12.0807,
+      "step": 250
+    },
+    {
+      "epoch": 2.5157232704402515,
+      "grad_norm": 0.029723290354013443,
+      "learning_rate": 4.107648725212465e-05,
+      "loss": 11.927,
+      "step": 300
+    },
+    {
+      "epoch": 2.9350104821802936,
+      "grad_norm": 0.08462727814912796,
+      "learning_rate": 5.6657223796034e-06,
+      "loss": 11.916,
+      "step": 350
+    },
+    {
+      "epoch": 2.9937106918238996,
+      "eval_loss": 11.916586875915527,
+      "eval_runtime": 0.4094,
+      "eval_samples_per_second": 246.686,
+      "eval_steps_per_second": 63.503,
+      "step": 357
     }
   ],
   "logging_steps": 50,
@@ -70,7 +99,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 268360826880.0,
+  "total_flos": 402378350592.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null