Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1ae7099966897d8de0a79191f801f1cbacd20b0cddd77953098111e808e13b
+oid sha256:0ef6a31932db3d7645bfd13636b528b64a70118b7e33a43c2a401bfa3e8bb61e
 size 81576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e639690d6ae5abdc370d09d3810363b4e814675ee0a51ded7d43c4abf4cdcc21
+oid sha256:bf646519b1d4c0aa3da561385f388c8d21d25c25162da00a454708ba556fa97c
 size 173094

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
+oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
 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": 0.004009355162044771,
+  "epoch": 0.008018710324089542,
   "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": 272.759,
       "eval_steps_per_second": 136.812,
       "step": 3
+    },
+    {
+      "epoch": 0.0053458068827263614,
+      "grad_norm": 0.25612157583236694,
+      "learning_rate": 8e-05,
+      "loss": 10.8384,
+      "step": 4
+    },
+    {
+      "epoch": 0.006682258603407952,
+      "grad_norm": 0.23330692946910858,
+      "learning_rate": 0.0001,
+      "loss": 10.8294,
+      "step": 5
+    },
+    {
+      "epoch": 0.008018710324089542,
+      "grad_norm": 0.17283666133880615,
+      "learning_rate": 0.00012,
+      "loss": 10.8429,
+      "step": 6
+    },
+    {
+      "epoch": 0.008018710324089542,
+      "eval_loss": 10.836779594421387,
+      "eval_runtime": 1.2036,
+      "eval_samples_per_second": 261.712,
+      "eval_steps_per_second": 131.272,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 492177457152.0,
+  "total_flos": 963847520256.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null