Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:986c6377786c6cdff929c2e8b6c12cd4744c5bc5c42bf2bd936704d500302639
+oid sha256:bcf47242fdb2d4bc4a70fb246887cdf47886b84caad800955c05be8efce1cb4d
 size 222865880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:867715343dd8be6a4269e0ec3b145ec6b19b7506bdc01673c2fd83fba7ccd344
+oid sha256:e098710ae320637de83726ef9158521fca79d9ac7438aeda0d1ea94b9ad9fbb9
 size 113528596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0fcad822500472c6ba26665425674104f55a36e5a73e943180e7dacc1590f8f
+oid sha256:8a9bfec275e3717cc57c1021fdb7bae65637cf0dc882fb7ab3d6099862b5f5f1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
+oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00469087156393658,
+  "epoch": 0.00938174312787316,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 9.158,
       "eval_steps_per_second": 4.579,
       "step": 50
+    },
+    {
+      "epoch": 0.005629045876723895,
+      "grad_norm": 0.6110089421272278,
+      "learning_rate": 0.0002,
+      "loss": 0.9785,
+      "step": 60
+    },
+    {
+      "epoch": 0.006567220189511211,
+      "grad_norm": 0.6589618921279907,
+      "learning_rate": 0.0002,
+      "loss": 1.2064,
+      "step": 70
+    },
+    {
+      "epoch": 0.007505394502298527,
+      "grad_norm": 0.6540957093238831,
+      "learning_rate": 0.0002,
+      "loss": 1.0105,
+      "step": 80
+    },
+    {
+      "epoch": 0.008443568815085843,
+      "grad_norm": 0.7634976506233215,
+      "learning_rate": 0.0002,
+      "loss": 0.97,
+      "step": 90
+    },
+    {
+      "epoch": 0.00938174312787316,
+      "grad_norm": 0.7584695816040039,
+      "learning_rate": 0.0002,
+      "loss": 0.9857,
+      "step": 100
+    },
+    {
+      "epoch": 0.00938174312787316,
+      "eval_loss": 0.5102854371070862,
+      "eval_runtime": 245.1252,
+      "eval_samples_per_second": 9.155,
+      "eval_steps_per_second": 4.577,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5999798607872e+16,
+  "total_flos": 3.1999597215744e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null