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:eee62e2fb2ca38cdf31a0bdc8cb8f9a8549959e806de67175298f80297876b7b
+oid sha256:026491cdfcad7e7a1b7246cc3ed182d12dd28de7bb325bee50dfd5595f7518e4
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d4f521d3bcf6355b99b571ce4fff1dfea3c980c8bfd967a322e277a9386ca63
+oid sha256:b937b78e1f215e34c16e5897d948d6e454688c27a13b5580e6efe1e44817633d
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:092c9317c326650f0000d23210645a05bcdc6f7f4048f7a1def2fe5ddacbeb6b
+oid sha256:e71ecadeaa9724540994972d976d719587c38099bbdccd7ce0ec9f1ea2e4391d
 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": 9.714632665452337e-05,
+  "epoch": 0.00019429265330904674,
   "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": 34.619,
       "eval_steps_per_second": 17.311,
       "step": 3
+    },
+    {
+      "epoch": 0.0001295284355393645,
+      "grad_norm": 2.8488619327545166,
+      "learning_rate": 8e-05,
+      "loss": 1.5003,
+      "step": 4
+    },
+    {
+      "epoch": 0.00016191054442420561,
+      "grad_norm": 2.439563512802124,
+      "learning_rate": 0.0001,
+      "loss": 1.2068,
+      "step": 5
+    },
+    {
+      "epoch": 0.00019429265330904674,
+      "grad_norm": 2.0994584560394287,
+      "learning_rate": 0.00012,
+      "loss": 1.2027,
+      "step": 6
+    },
+    {
+      "epoch": 0.00019429265330904674,
+      "eval_loss": 0.9562381505966187,
+      "eval_runtime": 377.6739,
+      "eval_samples_per_second": 34.429,
+      "eval_steps_per_second": 17.216,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 187536499015680.0,
+  "total_flos": 362570564763648.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null