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:b7183be861d54f81ac49a4edce72ddf004b552dcba713796b480a31556419df5
+oid sha256:d898712c150bbdc4e4638c28c56eb205a6d2ea591c22037f9a4826ec0765d005
 size 5327496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f8e9ff79c5e806fc5d8ca555c3bbc0d66e29efb62bef3fd72cb5c8f26b6b63
+oid sha256:d464fde61dbbb120c2722503afde5f79f24c933cc8fb3694e7f15b67bd4bb49b
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc789885519034ad36c177cac6d33f82aacac7ae82361b7f306c410b61694801
+oid sha256:dfdffa00fcbf23263244b002c2645ff4c50ab2041c7b30ed2dd004479b2b5f47
 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": 0.00023987526486227162,
+  "epoch": 0.00047975052972454323,
   "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": 109.174,
       "eval_steps_per_second": 54.587,
       "step": 3
+    },
+    {
+      "epoch": 0.00031983368648302884,
+      "grad_norm": 1.0127778053283691,
+      "learning_rate": 8e-05,
+      "loss": 3.1434,
+      "step": 4
+    },
+    {
+      "epoch": 0.000399792108103786,
+      "grad_norm": 0.6170755624771118,
+      "learning_rate": 0.0001,
+      "loss": 2.272,
+      "step": 5
+    },
+    {
+      "epoch": 0.00047975052972454323,
+      "grad_norm": 0.777292013168335,
+      "learning_rate": 0.00012,
+      "loss": 2.9915,
+      "step": 6
+    },
+    {
+      "epoch": 0.00047975052972454323,
+      "eval_loss": 0.6983044743537903,
+      "eval_runtime": 48.7238,
+      "eval_samples_per_second": 108.079,
+      "eval_steps_per_second": 54.039,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7427950903296.0,
+  "total_flos": 16447605571584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null