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:fe5f5a60ac3e34a2af8b519b8eeaaf5d779fa4ab69da052bf0eadd77bc11e3d5
+oid sha256:ed867fe682a35665d9cd6bd40bf9332f9d8f70f903761f1e4f0e31633bcb480f
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd1abb3ecb10b27cd140ed6ff1c5d1af4b139909966d4d9d3c77ecf1712e2a80
+oid sha256:7560292d3777baa584fe0425bd64ed3bff3f81ad2752b43361255ee6af613f00
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6afa667d786041a5d437256f7581610ca504ade2765fe479e32f1a5d5d607678
+oid sha256:b15136f5d879e4ff194d1576a3a9b5574ef7137f2137749ff8ef2fca741d6220
 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": 5.592293819117256e-05,
+  "epoch": 0.00011184587638234512,
   "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": 28.962,
       "eval_steps_per_second": 14.481,
       "step": 3
+    },
+    {
+      "epoch": 7.456391758823009e-05,
+      "grad_norm": 1.0699489116668701,
+      "learning_rate": 8e-05,
+      "loss": 2.393,
+      "step": 4
+    },
+    {
+      "epoch": 9.320489698528761e-05,
+      "grad_norm": 1.1504356861114502,
+      "learning_rate": 0.0001,
+      "loss": 2.5008,
+      "step": 5
+    },
+    {
+      "epoch": 0.00011184587638234512,
+      "grad_norm": 0.9129418730735779,
+      "learning_rate": 0.00012,
+      "loss": 2.2523,
+      "step": 6
+    },
+    {
+      "epoch": 0.00011184587638234512,
+      "eval_loss": 2.2946419715881348,
+      "eval_runtime": 781.5975,
+      "eval_samples_per_second": 28.9,
+      "eval_steps_per_second": 14.45,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 212541365551104.0,
+  "total_flos": 475092464173056.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null