Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8491b92a0d813f8cb0a258aa96a13ad7450786469a20d6515c80d4a2c9176425
+oid sha256:54ad9ce7ee48c544024263e856db146d4fe299e49d64c1d53a4f83d60039fa23
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46c7e8d6e51cdd89973d274cb55c4aee29ce43be093c8303df27afe0999692aa
+oid sha256:175543af9e11714a2c3386976cbcc2714cdf25800c6bab5827d344a78c753b97
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b9d7e72a62eb3b133ef0a55f60fb21be5b26b801d3cf1df1ca1b266bfd717e6
+oid sha256:293f7bf9fcecc3ab745508812aa10de0e20eefbfd21dc5078d377caf6769f573
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ef0e768220ab06b0b8ca60bf0cb82c3ba1ffa61503120e1cf6e3622be29cf83
+oid sha256:053f8a597fb71bde446a175404cc18fe6996cf501293c3abfb94953dfd03d780
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01133385280158674,
+  "epoch": 0.015111803735448986,
   "eval_steps": 10,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -39,6 +39,21 @@
       "eval_samples_per_second": 7.351,
       "eval_steps_per_second": 3.676,
       "step": 30
+    },
+    {
+      "epoch": 0.015111803735448986,
+      "grad_norm": 0.5035961866378784,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 1.3002,
+      "step": 40
+    },
+    {
+      "epoch": 0.015111803735448986,
+      "eval_loss": 1.244433045387268,
+      "eval_runtime": 595.3628,
+      "eval_samples_per_second": 7.488,
+      "eval_steps_per_second": 3.744,
+      "step": 40
     }
   ],
   "logging_steps": 40,
@@ -58,7 +73,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.97738750803968e+16,
+  "total_flos": 2.63651667738624e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null