Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:886c59ffd2d022b9f1f4c8fa5608052b6a3e426f8bdf7970de7a365e0fd67211
+oid sha256:045ed157e961c3c5135fe04a23cc0be459b1143c511a42b3311b51d26ceec08c
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfd799fe6ee551e5da84785f4f0084b885941e0c9e0069cf9980f0fccd3ea891
+oid sha256:cea4d8774bf4602507db83114914611b52e65d2c34d4c143fb399cd12f5e8c6a
 size 3633466

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424d06375131df3df5d4883391c61f995c66d877e893fd245f2c624058954297
+oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4865497076023392,
+  "epoch": 0.7298245614035088,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 167.931,
       "eval_steps_per_second": 83.965,
       "step": 26
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.5672177076339722,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 3.1356,
+      "step": 27
+    },
+    {
+      "epoch": 0.5239766081871345,
+      "grad_norm": 0.5034229159355164,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 3.3106,
+      "step": 28
+    },
+    {
+      "epoch": 0.5426900584795321,
+      "grad_norm": 0.3882250487804413,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 2.9574,
+      "step": 29
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 0.40193095803260803,
+      "learning_rate": 5e-05,
+      "loss": 2.8383,
+      "step": 30
+    },
+    {
+      "epoch": 0.5801169590643275,
+      "grad_norm": 0.4183836877346039,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 3.0697,
+      "step": 31
+    },
+    {
+      "epoch": 0.5988304093567252,
+      "grad_norm": 0.43808770179748535,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 3.0987,
+      "step": 32
+    },
+    {
+      "epoch": 0.6175438596491228,
+      "grad_norm": 0.4170209765434265,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 3.2466,
+      "step": 33
+    },
+    {
+      "epoch": 0.6362573099415205,
+      "grad_norm": 0.4159402847290039,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.8567,
+      "step": 34
+    },
+    {
+      "epoch": 0.6549707602339181,
+      "grad_norm": 0.4351010024547577,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.091,
+      "step": 35
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 0.4126148223876953,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 2.8086,
+      "step": 36
+    },
+    {
+      "epoch": 0.6923976608187135,
+      "grad_norm": 0.41550347208976746,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 3.1724,
+      "step": 37
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.4178273379802704,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 3.0974,
+      "step": 38
+    },
+    {
+      "epoch": 0.7298245614035088,
+      "grad_norm": 0.4026312828063965,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 2.957,
+      "step": 39
+    },
+    {
+      "epoch": 0.7298245614035088,
+      "eval_loss": 2.982048273086548,
+      "eval_runtime": 0.5374,
+      "eval_samples_per_second": 167.458,
+      "eval_steps_per_second": 83.729,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 691854223343616.0,
+  "total_flos": 1033923411836928.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null