Training in progress, step 336, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcc7c1bb49029978b38479c4be7f1ef61c6a2f919bd26fa335b25ed148c05645
+oid sha256:abb56d38a89e7b62a7798d623f95ec7bceb0800b1e0e250ab37ccd5fc69a012a
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc3812fdb507dc890ad3dfeb461b18c142361e92db1a8d19d6b3dbcdb50cb254
+oid sha256:e53496acb3ee81f29db8e8dd644eb76ba4b47ccf9f2ab343ac4a3ae57576051b
 size 102864868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fd586e160e28252df6d0804518bcfa9955584c079b4b4506e38e98dfc07096c
+oid sha256:207840526dea4fa9627489a495e4077d47d6217bc1c29fded5fdb4cce6503140
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:318b114b83c26bcba11815378a88e0015bce044b0002c702e0a2627e1a1d1e56
+oid sha256:10affc9ced28dcfaf0d40e3497a97c8e7416bd057324538f99a7e1756fd84408
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.061628760088041086,
+  "epoch": 0.07043286867204696,
   "eval_steps": 42,
-  "global_step": 294,
+  "global_step": 336,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -757,6 +757,112 @@
       "eval_samples_per_second": 48.701,
       "eval_steps_per_second": 6.091,
       "step": 294
+    },
+    {
+      "epoch": 0.06225762498689865,
+      "grad_norm": 0.36433523893356323,
+      "learning_rate": 3.6698157721666246e-05,
+      "loss": 1.0619,
+      "step": 297
+    },
+    {
+      "epoch": 0.06288648988575621,
+      "grad_norm": 0.382252961397171,
+      "learning_rate": 3.5773620668448384e-05,
+      "loss": 1.0544,
+      "step": 300
+    },
+    {
+      "epoch": 0.06351535478461377,
+      "grad_norm": 0.4051714539527893,
+      "learning_rate": 3.48543465876014e-05,
+      "loss": 0.9961,
+      "step": 303
+    },
+    {
+      "epoch": 0.06414421968347134,
+      "grad_norm": 0.34751641750335693,
+      "learning_rate": 3.3940675559617724e-05,
+      "loss": 1.0396,
+      "step": 306
+    },
+    {
+      "epoch": 0.0647730845823289,
+      "grad_norm": 0.38340121507644653,
+      "learning_rate": 3.303294559217063e-05,
+      "loss": 1.0916,
+      "step": 309
+    },
+    {
+      "epoch": 0.06540194948118645,
+      "grad_norm": 0.41020599007606506,
+      "learning_rate": 3.213149249506997e-05,
+      "loss": 1.0738,
+      "step": 312
+    },
+    {
+      "epoch": 0.06603081438004402,
+      "grad_norm": 0.3864920735359192,
+      "learning_rate": 3.12366497560313e-05,
+      "loss": 1.0936,
+      "step": 315
+    },
+    {
+      "epoch": 0.06665967927890158,
+      "grad_norm": 0.35983094573020935,
+      "learning_rate": 3.0348748417303823e-05,
+      "loss": 1.1001,
+      "step": 318
+    },
+    {
+      "epoch": 0.06728854417775915,
+      "grad_norm": 0.39053815603256226,
+      "learning_rate": 2.9468116953203107e-05,
+      "loss": 1.0366,
+      "step": 321
+    },
+    {
+      "epoch": 0.06791740907661671,
+      "grad_norm": 0.3519478142261505,
+      "learning_rate": 2.8595081148593738e-05,
+      "loss": 1.044,
+      "step": 324
+    },
+    {
+      "epoch": 0.06854627397547428,
+      "grad_norm": 0.37353023886680603,
+      "learning_rate": 2.772996397836704e-05,
+      "loss": 1.0449,
+      "step": 327
+    },
+    {
+      "epoch": 0.06917513887433183,
+      "grad_norm": 0.357658714056015,
+      "learning_rate": 2.687308548795825e-05,
+      "loss": 1.0519,
+      "step": 330
+    },
+    {
+      "epoch": 0.06980400377318939,
+      "grad_norm": 0.40195825695991516,
+      "learning_rate": 2.6024762674947313e-05,
+      "loss": 1.0915,
+      "step": 333
+    },
+    {
+      "epoch": 0.07043286867204696,
+      "grad_norm": 0.3929975628852844,
+      "learning_rate": 2.5185309371787513e-05,
+      "loss": 1.0375,
+      "step": 336
+    },
+    {
+      "epoch": 0.07043286867204696,
+      "eval_loss": 1.0703336000442505,
+      "eval_runtime": 165.0152,
+      "eval_samples_per_second": 48.692,
+      "eval_steps_per_second": 6.09,
+      "step": 336
     }
   ],
   "logging_steps": 3,
@@ -776,7 +882,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.271454686268621e+16,
+  "total_flos": 7.167376784306995e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null