Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6535271cfec8fa867042d13b30861bd9275ebd7afd16d7dbac2682831060886f
+oid sha256:72c6a63130f40f892734d33c4e7fba49040576a82597b18285bc242c05dde612
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df4ff3bcda0b443b0e3fab4594bd5f3703f9813338b28f1120a4fb6fea38835c
+oid sha256:d915bd193fada06c440790ebcc8814d49c1965ef1ff4e1956268866c9eb796fc
 size 1003002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca91fc1d18931263c318f79aaa62f856c567e7bb9ed0ac3b24cabf4efb347568
+oid sha256:ae596888a63c03586377673bda3da0862fda255f512ebfa49851277059dd39e1
 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": 0.056074766355140186,
+  "epoch": 0.11214953271028037,
   "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": 35.994,
       "eval_steps_per_second": 18.78,
       "step": 3
+    },
+    {
+      "epoch": 0.07476635514018691,
+      "grad_norm": 12.276077270507812,
+      "learning_rate": 8e-05,
+      "loss": 8.4937,
+      "step": 4
+    },
+    {
+      "epoch": 0.09345794392523364,
+      "grad_norm": 13.09289836883545,
+      "learning_rate": 0.0001,
+      "loss": 8.1714,
+      "step": 5
+    },
+    {
+      "epoch": 0.11214953271028037,
+      "grad_norm": 12.53107738494873,
+      "learning_rate": 0.00012,
+      "loss": 8.1098,
+      "step": 6
+    },
+    {
+      "epoch": 0.11214953271028037,
+      "eval_loss": 7.94780158996582,
+      "eval_runtime": 0.6902,
+      "eval_samples_per_second": 33.324,
+      "eval_steps_per_second": 17.387,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1628971204608.0,
+  "total_flos": 3257942409216.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null