Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9190852d802dd3f5a3cbf15ea99d23f6616b518d0f73bf543154d0ccf512b2c0
+oid sha256:12f5405331d39189539a9b2893123594f30fabac72611f502cf2264947f2d63c
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8b1acea77093733aa7e8b3df3d0f3f7e2b68d6cade25ae2aacb2b8afb1cd756
+oid sha256:3be870ce6b637db75f6e6f7243785a6e2dfae43cf65d93b92143bfbe75719d1c
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa1e96725392fca175b7dab8b8592d8fb0dd052ccba8154ca08cf1551f7e0023
+oid sha256:32f6349df5bee30fdab4c130bb4c0660319891f0bdf71b474b07934a8c01da8b
 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": 0.0012759170653907496,
+  "epoch": 0.002551834130781499,
   "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": 27.78,
       "eval_steps_per_second": 13.89,
       "step": 3
+    },
+    {
+      "epoch": 0.0017012227538543328,
+      "grad_norm": 0.30784478783607483,
+      "learning_rate": 8e-05,
+      "loss": 1.5413,
+      "step": 4
+    },
+    {
+      "epoch": 0.002126528442317916,
+      "grad_norm": 0.3248178958892822,
+      "learning_rate": 0.0001,
+      "loss": 1.7453,
+      "step": 5
+    },
+    {
+      "epoch": 0.002551834130781499,
+      "grad_norm": 0.3052712082862854,
+      "learning_rate": 0.00012,
+      "loss": 1.5164,
+      "step": 6
+    },
+    {
+      "epoch": 0.002551834130781499,
+      "eval_loss": 1.594720721244812,
+      "eval_runtime": 36.0722,
+      "eval_samples_per_second": 27.445,
+      "eval_steps_per_second": 13.722,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 153475186950144.0,
+  "total_flos": 306950373900288.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null