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:f6e73ee14a45089a80d5ad3a5d797a8d7ae75ec78ab96be86e2cecd5767d3b76
+oid sha256:865c80d04ad16537d66f84556180a051f49ac7f94dafc5e339f6f8b5e726cd8f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45a9280a6e87b314fec070729bad7d06670c712f9e9f382c68b35b152379e525
+oid sha256:39b6cb09e2218143b607ec4d6cab30fd4bf49d5360525485d9579ceb2f109e6a
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b1f7e74c92417dc92a8539c0a584056c35b4274a3fb049888a84cd57047e99c
+oid sha256:b16e571b5200a459b1d8d0f1e526ee8e68933e666abc123060b4e85c87c58aaf
 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": 0.0009224383119378892,
+  "epoch": 0.0018448766238757784,
   "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": 30.617,
       "eval_steps_per_second": 15.308,
       "step": 3
+    },
+    {
+      "epoch": 0.001229917749250519,
+      "grad_norm": 1.700682282447815,
+      "learning_rate": 8e-05,
+      "loss": 2.3701,
+      "step": 4
+    },
+    {
+      "epoch": 0.0015373971865631486,
+      "grad_norm": 1.8919302225112915,
+      "learning_rate": 0.0001,
+      "loss": 2.8062,
+      "step": 5
+    },
+    {
+      "epoch": 0.0018448766238757784,
+      "grad_norm": 1.9330875873565674,
+      "learning_rate": 0.00012,
+      "loss": 2.5166,
+      "step": 6
+    },
+    {
+      "epoch": 0.0018448766238757784,
+      "eval_loss": 2.944230556488037,
+      "eval_runtime": 44.8463,
+      "eval_samples_per_second": 30.549,
+      "eval_steps_per_second": 15.274,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 647347486851072.0,
+  "total_flos": 1202216761294848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null