Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39a9a728207d42ac6a199e9c711ee737900a0c1f2afe28cdccae5659f9c905d4
+oid sha256:4597d17c81909b050ea465530b71fbdf4c0117a964053232c52421552355a268
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d413dd7e3eaf63619a70550c03fd6cf2a570a973eb8da7044db177b79b648e39
+oid sha256:4ab00b71b8686c641f7a3395cb443759964fafefa65da11488ee995bf99191f4
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2355e43fd44f1d9860c59f45b4d1039afaad0a42f79d076c0667863cd27cb0
+oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
 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": 0.0016922859963333804,
+  "epoch": 0.0033845719926667607,
   "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": 29.271,
       "eval_steps_per_second": 14.655,
       "step": 3
+    },
+    {
+      "epoch": 0.0022563813284445073,
+      "grad_norm": 3.8727877140045166,
+      "learning_rate": 8e-05,
+      "loss": 13.6571,
+      "step": 4
+    },
+    {
+      "epoch": 0.0028204766605556338,
+      "grad_norm": 4.041762351989746,
+      "learning_rate": 0.0001,
+      "loss": 12.1829,
+      "step": 5
+    },
+    {
+      "epoch": 0.0033845719926667607,
+      "grad_norm": 5.419154167175293,
+      "learning_rate": 0.00012,
+      "loss": 13.0971,
+      "step": 6
+    },
+    {
+      "epoch": 0.0033845719926667607,
+      "eval_loss": 3.3201839923858643,
+      "eval_runtime": 25.7789,
+      "eval_samples_per_second": 28.977,
+      "eval_steps_per_second": 14.508,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 488619940773888.0,
+  "total_flos": 977239881547776.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null