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:a0454ee5ac5d61760144c2ce7e8e8a0481ba9310775f2ca6d17b5261031fe46b
+oid sha256:ebbfeff6403ce513d84e9018b3ff083e79c2aaf04e6c4425f1a76354ea97c46e
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09289911e3f68f759a2c9393cd7fd40b5f3954cf5884365752230436f0f327f1
+oid sha256:57fc69a3cf32e1859036899582b4a5b4b8979d0fb7379a04da050980903b8ee8
 size 63974

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": 0.0014278914802475012,
+  "epoch": 0.0028557829604950024,
   "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": 366.887,
       "eval_steps_per_second": 183.651,
       "step": 3
+    },
+    {
+      "epoch": 0.0019038553069966682,
+      "grad_norm": 0.15274536609649658,
+      "learning_rate": 8e-05,
+      "loss": 10.3817,
+      "step": 4
+    },
+    {
+      "epoch": 0.002379819133745835,
+      "grad_norm": 0.1628134399652481,
+      "learning_rate": 0.0001,
+      "loss": 10.3795,
+      "step": 5
+    },
+    {
+      "epoch": 0.0028557829604950024,
+      "grad_norm": 0.1442088484764099,
+      "learning_rate": 0.00012,
+      "loss": 10.3776,
+      "step": 6
+    },
+    {
+      "epoch": 0.0028557829604950024,
+      "eval_loss": 10.37758731842041,
+      "eval_runtime": 2.476,
+      "eval_samples_per_second": 357.432,
+      "eval_steps_per_second": 178.918,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 38792724480.0,
+  "total_flos": 77585448960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null