Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca2ef0261b9297e57eb0e6889cbd70bd9fc32b7ddb742c7a9bd122e427882cb1
+oid sha256:7ecd3fcfd27e49fb495aa7bbbb129b568be74649b4844b9100dd6cddbde009a3
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:623c8669599ab8606c91a89f68efd3817190db7cebdd8f7009d841dfbc06cf13
+oid sha256:4c9f5f459b9bf75c0f92d2c4fc5b231f3fd10804adca800379d25a295af7c0c3
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c512fb5e6f5d109f5378fc46a214147599d5eb7b9ff95241caad816b4b88a833
+oid sha256:297782d51f5f3ca2aeca82fbf7c6fb703c25807edcab7ced77a16f88131b5dce
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
+oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04608294930875576,
+  "epoch": 0.06912442396313365,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 27.776,
       "eval_steps_per_second": 13.888,
       "step": 100
+    },
+    {
+      "epoch": 0.05069124423963134,
+      "grad_norm": 1.0844675302505493,
+      "learning_rate": 0.0002,
+      "loss": 1.2192,
+      "step": 110
+    },
+    {
+      "epoch": 0.055299539170506916,
+      "grad_norm": 0.8243290185928345,
+      "learning_rate": 0.0002,
+      "loss": 1.2125,
+      "step": 120
+    },
+    {
+      "epoch": 0.059907834101382486,
+      "grad_norm": 0.940923273563385,
+      "learning_rate": 0.0002,
+      "loss": 1.2913,
+      "step": 130
+    },
+    {
+      "epoch": 0.06451612903225806,
+      "grad_norm": 0.918209969997406,
+      "learning_rate": 0.0002,
+      "loss": 1.2533,
+      "step": 140
+    },
+    {
+      "epoch": 0.06912442396313365,
+      "grad_norm": 0.9641485214233398,
+      "learning_rate": 0.0002,
+      "loss": 1.2138,
+      "step": 150
+    },
+    {
+      "epoch": 0.06912442396313365,
+      "eval_loss": 1.1654969453811646,
+      "eval_runtime": 32.9162,
+      "eval_samples_per_second": 27.767,
+      "eval_steps_per_second": 13.884,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.2828532203782144e+16,
+  "total_flos": 3.4024968799911936e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null