Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99bf33a9f1a51e9d4100cab958e1f7a54336c26fa0097a119d0d0b0b774ba9cf
+oid sha256:ea497b09ecc2329e47b90619725037b860efea32c122757fd121c4ff2a841974
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:379026e7745d3f4211172ddf8ff1af6f43166a77d0d038d63eb85dbf5f5169f8
+oid sha256:8ee301d40797258d16889045efa2a550358457198575706a230c4f3ec3c43a2c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
+oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
 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": 0.0005658242172764995,
+  "epoch": 0.001131648434552999,
   "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": 31.486,
       "eval_steps_per_second": 15.75,
       "step": 3
+    },
+    {
+      "epoch": 0.0007544322897019992,
+      "grad_norm": 9.758016586303711,
+      "learning_rate": 8e-05,
+      "loss": 3.4399,
+      "step": 4
+    },
+    {
+      "epoch": 0.000943040362127499,
+      "grad_norm": 19.836227416992188,
+      "learning_rate": 0.0001,
+      "loss": 4.7794,
+      "step": 5
+    },
+    {
+      "epoch": 0.001131648434552999,
+      "grad_norm": 12.299468040466309,
+      "learning_rate": 0.00012,
+      "loss": 3.0613,
+      "step": 6
+    },
+    {
+      "epoch": 0.001131648434552999,
+      "eval_loss": 0.9074329733848572,
+      "eval_runtime": 68.176,
+      "eval_samples_per_second": 32.753,
+      "eval_steps_per_second": 16.384,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 525801539764224.0,
+  "total_flos": 1051603079528448.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null