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:ae134784f1ac2fc665cb9bb3babb6353a6ed06c55e341969b4e4b34fd85472db
+oid sha256:1b063f794e8d905c44caa125b66183707a1dde48973e3276ff28d2c4c531785f
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68aa9325e73d1d3b771d0e7b711b5f9c8c847aa0992b631c072df47d104b7a00
+oid sha256:d7c8ea1ef0d1661206fbbce0145f1e033d65e42959edba13fa92aec62fc39809
 size 41459700

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": 0.0702346783724464,
+  "epoch": 0.10535201755866959,
   "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": 28.989,
       "eval_steps_per_second": 14.494,
       "step": 26
+    },
+    {
+      "epoch": 0.07293601215600203,
+      "grad_norm": 0.2152528017759323,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 1.2901,
+      "step": 27
+    },
+    {
+      "epoch": 0.07563734593955766,
+      "grad_norm": 0.22586144506931305,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 1.1882,
+      "step": 28
+    },
+    {
+      "epoch": 0.07833867972311329,
+      "grad_norm": 0.22725199162960052,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 1.1866,
+      "step": 29
+    },
+    {
+      "epoch": 0.08104001350666892,
+      "grad_norm": 0.20386184751987457,
+      "learning_rate": 5e-05,
+      "loss": 1.1657,
+      "step": 30
+    },
+    {
+      "epoch": 0.08374134729022455,
+      "grad_norm": 0.2280956506729126,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 1.2514,
+      "step": 31
+    },
+    {
+      "epoch": 0.08644268107378018,
+      "grad_norm": 0.210204616189003,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.0071,
+      "step": 32
+    },
+    {
+      "epoch": 0.08914401485733581,
+      "grad_norm": 0.21837709844112396,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 1.147,
+      "step": 33
+    },
+    {
+      "epoch": 0.09184534864089144,
+      "grad_norm": 0.23454667627811432,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.0993,
+      "step": 34
+    },
+    {
+      "epoch": 0.09454668242444707,
+      "grad_norm": 0.22570019960403442,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1352,
+      "step": 35
+    },
+    {
+      "epoch": 0.0972480162080027,
+      "grad_norm": 0.20457398891448975,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 1.1004,
+      "step": 36
+    },
+    {
+      "epoch": 0.09994934999155833,
+      "grad_norm": 0.20898611843585968,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 1.0908,
+      "step": 37
+    },
+    {
+      "epoch": 0.10265068377511397,
+      "grad_norm": 0.21299485862255096,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.1544,
+      "step": 38
+    },
+    {
+      "epoch": 0.10535201755866959,
+      "grad_norm": 0.19731168448925018,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 1.1738,
+      "step": 39
+    },
+    {
+      "epoch": 0.10535201755866959,
+      "eval_loss": 1.2369698286056519,
+      "eval_runtime": 21.5205,
+      "eval_samples_per_second": 28.996,
+      "eval_steps_per_second": 14.498,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.006047179505664e+16,
+  "total_flos": 4.487287818682368e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null