Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b291ca0de73e18830c9ee0c654ca3c54325fe3bb9f8ff6ef56e5143b01b3f72
+oid sha256:cb503ccfa210215d360d27f8c47131d03eb5c5667576cdd6b8b900270751c898
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff59a55dd02d18c8fecb23e1fb1c551490f4ee1b0450fbd84ae5c87abbb4d5c4
+oid sha256:65b4dbbe2e571456e44afa3246a60f181ffdaffef8805fdf1303389b146c5d8d
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b69ab2fe919869fa2a6cb9088e983d756e79d4cb4559790a464522732c46806a
+oid sha256:a7a168dfcfd0ce1ccbacd396224b03b5e80f0ddf15f2d4e9f23c73a23afec595
 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": 0.007623888182973317,
+  "epoch": 0.015247776365946633,
   "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": 40.778,
       "eval_steps_per_second": 20.389,
       "step": 3
+    },
+    {
+      "epoch": 0.010165184243964422,
+      "grad_norm": 0.4207238256931305,
+      "learning_rate": 8e-05,
+      "loss": 5.4398,
+      "step": 4
+    },
+    {
+      "epoch": 0.012706480304955527,
+      "grad_norm": 0.40501707792282104,
+      "learning_rate": 0.0001,
+      "loss": 5.4969,
+      "step": 5
+    },
+    {
+      "epoch": 0.015247776365946633,
+      "grad_norm": 0.26661601662635803,
+      "learning_rate": 0.00012,
+      "loss": 5.4325,
+      "step": 6
+    },
+    {
+      "epoch": 0.015247776365946633,
+      "eval_loss": 5.472946643829346,
+      "eval_runtime": 4.1557,
+      "eval_samples_per_second": 39.945,
+      "eval_steps_per_second": 19.972,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 205681990828032.0,
+  "total_flos": 445644313460736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null