Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbc0afb24909aed9029fc1c9b559cfe4e6334838959e75ee4c0b05fa1b5ae044
+oid sha256:d6bc17fca2b8b903c5da830bee10f77a5bc14838bfde6e70e91224f80c045105
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a92db07c67dc595a6c675c3f730423c6c6d676d1664f479460a1703ba2b6c4d1
+oid sha256:e6c058eddd7b6e884adf77510f4b4bf02be0b70bcca951026cce48f2c4d8fc4b
 size 21354682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:368a219c1dbfdf1d718c6ec293bbfe1fece166bbd912b6a6eeb44b0f2e7bc053
+oid sha256:138ba6553b3dbae40c3fb253efb06aa37ebf255f096fc16c7eed748f00fed1dd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec942292267bb06cc495f28f765abdfdf101d23971c1de481c4ea2a744d43b7
+oid sha256:2d01151db1fc4f9c05131abecdc90435e3aab7eb2c3021fc926311286e779587
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03307607497243661,
+  "epoch": 0.044101433296582136,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,43 @@
       "eval_samples_per_second": 31.404,
       "eval_steps_per_second": 15.702,
       "step": 30
+    },
+    {
+      "epoch": 0.03638368246968027,
+      "grad_norm": 2.643308162689209,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 12.4712,
+      "step": 33
+    },
+    {
+      "epoch": 0.03858875413450937,
+      "eval_loss": 3.0755653381347656,
+      "eval_runtime": 12.1852,
+      "eval_samples_per_second": 31.35,
+      "eval_steps_per_second": 15.675,
+      "step": 35
+    },
+    {
+      "epoch": 0.03969128996692393,
+      "grad_norm": 2.3923370838165283,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 12.7681,
+      "step": 36
+    },
+    {
+      "epoch": 0.04299889746416759,
+      "grad_norm": 2.5252928733825684,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 12.5758,
+      "step": 39
+    },
+    {
+      "epoch": 0.044101433296582136,
+      "eval_loss": 3.0728816986083984,
+      "eval_runtime": 12.6924,
+      "eval_samples_per_second": 30.097,
+      "eval_steps_per_second": 15.048,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -147,12 +184,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 257590145581056.0,
+  "total_flos": 343812788453376.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null