Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:140126756432365611ce8233470a75021c6f4731332bcdeff97f8c8712e1ed2d
+oid sha256:9a1a412b4417b09db633fe1f785b0a65830420fa8e4be125a617d4dd85fe1e62
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55646d99981d1750f46831af419696e5f09f4e827411092d32b19f4776469d23
+oid sha256:5c421ca5210fe7fbd13a4fd15c9d33224cb6011c7cd232cfdd1ce8cfd025f2ac
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a75ae50ef05b0af49c3969f35c925149f1546408e414606cff98807664e1d74
+oid sha256:58172de5502b3aa1c59bc9671fc2db0288d4d215bc0e3ddf041f8963fc20488a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007134363852556481,
+  "epoch": 0.014268727705112961,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 82.346,
       "eval_steps_per_second": 41.173,
       "step": 3
+    },
+    {
+      "epoch": 0.009512485136741973,
+      "grad_norm": 25.129722595214844,
+      "learning_rate": 8e-05,
+      "loss": 10.9121,
+      "step": 4
+    },
+    {
+      "epoch": 0.011890606420927468,
+      "grad_norm": 28.124937057495117,
+      "learning_rate": 0.0001,
+      "loss": 11.458,
+      "step": 5
+    },
+    {
+      "epoch": 0.014268727705112961,
+      "grad_norm": 26.849044799804688,
+      "learning_rate": 0.00012,
+      "loss": 11.4832,
+      "step": 6
+    },
+    {
+      "epoch": 0.014268727705112961,
+      "eval_loss": 2.750887393951416,
+      "eval_runtime": 2.1839,
+      "eval_samples_per_second": 81.506,
+      "eval_steps_per_second": 40.753,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 30704998023168.0,
+  "total_flos": 63603210190848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null