Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ce4efe7cbc5fc46a66d3b44292d06a599dd99238138068eb267fbc22d77302
+oid sha256:28b4444d895fa5a08ceb087871ee3fc6281105cd5c94240e89917ee899ba1122
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:786c42c9d562f8f857b4b8b820fd829cf3fa0e503e9baedc3f2c523a7d4232e4
+oid sha256:c453768a676d1e0b8e6a9091fc288277e4e9fa4fb7ff12156fbccfe8b33f02c4
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd264efeafada3ad39db346d459a2ad8b086f19b71ccb05fd8d1a5c0d284f9ae
+oid sha256:6ec54827547718f4c97d4a5e121a3be903aca4b7e01859f0f8d62916134f2417
 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": 3.36931953784167e-05,
+  "epoch": 6.73863907568334e-05,
   "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": 14.443,
       "eval_steps_per_second": 7.221,
       "step": 3
+    },
+    {
+      "epoch": 4.49242605045556e-05,
+      "grad_norm": 1.056449294090271,
+      "learning_rate": 8e-05,
+      "loss": 4.9529,
+      "step": 4
+    },
+    {
+      "epoch": 5.61553256306945e-05,
+      "grad_norm": 1.198383092880249,
+      "learning_rate": 0.0001,
+      "loss": 4.6338,
+      "step": 5
+    },
+    {
+      "epoch": 6.73863907568334e-05,
+      "grad_norm": 0.8677435517311096,
+      "learning_rate": 0.00012,
+      "loss": 3.8863,
+      "step": 6
+    },
+    {
+      "epoch": 6.73863907568334e-05,
+      "eval_loss": 1.0128856897354126,
+      "eval_runtime": 2598.0382,
+      "eval_samples_per_second": 14.43,
+      "eval_steps_per_second": 7.215,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1503946982031360.0,
+  "total_flos": 3166204172697600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null