Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a730cfa3113f34e4ad4af5c2f2a59b07f50dd259774f50f39192d74581a676d
+oid sha256:a8f0fc7c20ffc9cfd69ed661d9e1e1dae9ebaa9ad752e92860846fa4302c5ea9
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c91bd1de337d46b23d6d092ba19fc8577919225b964b0c79860839a1400930c
+oid sha256:4c24e405533b4e9b216b37b7f54fc83d3779e46afc6329eb312ba1b5ab3c9664
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d63550aef934dca682dbe4a2a94ff2b1a5fd333f064103ac7badea775ed97a9
+oid sha256:7a8fbdd40f7edc9d5266c41a92e911a33f810a381088729bf4c84d9fe8f8cfae
 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": 0.0003116316513880593,
+  "epoch": 0.0006232633027761186,
   "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": 35.831,
       "eval_steps_per_second": 17.915,
       "step": 3
+    },
+    {
+      "epoch": 0.00041550886851741243,
+      "grad_norm": 1.465193510055542,
+      "learning_rate": 8e-05,
+      "loss": 1.8448,
+      "step": 4
+    },
+    {
+      "epoch": 0.0005193860856467655,
+      "grad_norm": 1.385634422302246,
+      "learning_rate": 0.0001,
+      "loss": 1.8131,
+      "step": 5
+    },
+    {
+      "epoch": 0.0006232633027761186,
+      "grad_norm": 1.5537233352661133,
+      "learning_rate": 0.00012,
+      "loss": 1.8471,
+      "step": 6
+    },
+    {
+      "epoch": 0.0006232633027761186,
+      "eval_loss": 1.7395198345184326,
+      "eval_runtime": 112.8668,
+      "eval_samples_per_second": 35.918,
+      "eval_steps_per_second": 17.959,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 162531632480256.0,
+  "total_flos": 312560831692800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null