Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c5118aabf6f70f7f53f3a4f7720dcad1ee071e5815507bb7fde487252693a48
+oid sha256:738cfe61ccda591f2a74655ea80239a150784904063b046346e0b6dc27f48251
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:888e1c0d823cbe9fb6ed25c9bbaaa5f5e646dc1c78e2120f2fd56c55f3f12a43
+oid sha256:193221e530bc1326d1607ccf86c9116f4bb619888a75dcb15ebe25c2732f3324
 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": 0.00045322355251727916,
+  "epoch": 0.0009064471050345583,
   "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": 32.555,
       "eval_steps_per_second": 16.284,
       "step": 3
+    },
+    {
+      "epoch": 0.0006042980700230389,
+      "grad_norm": 0.3123856782913208,
+      "learning_rate": 8e-05,
+      "loss": 1.238,
+      "step": 4
+    },
+    {
+      "epoch": 0.0007553725875287985,
+      "grad_norm": 0.3366721272468567,
+      "learning_rate": 0.0001,
+      "loss": 1.3196,
+      "step": 5
+    },
+    {
+      "epoch": 0.0009064471050345583,
+      "grad_norm": 0.4621126651763916,
+      "learning_rate": 0.00012,
+      "loss": 1.53,
+      "step": 6
+    },
+    {
+      "epoch": 0.0009064471050345583,
+      "eval_loss": 1.3454577922821045,
+      "eval_runtime": 85.7135,
+      "eval_samples_per_second": 32.515,
+      "eval_steps_per_second": 16.263,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 554869274443776.0,
+  "total_flos": 1109738548887552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null