Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71e6bbeee4c09b498336a9d4cc55024fcdcba2745aaaf3ff9ab50b1f636678dd
+oid sha256:63731732930714c8288f45995166202ee28781533bbcad614ee4457098bef4f6
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48c3f0e3d4373be5ea805c6431d8028dd9ec1d7d24d08944e251f4ea7c4c61ff
+oid sha256:c458d9919f58ebe8044ca07e2d3aec43edde945c8cb34fc55084765f3d13a9ed
 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": 0.0044411547002220575,
+  "epoch": 0.008882309400444115,
   "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": 250.233,
       "eval_steps_per_second": 125.556,
       "step": 3
+    },
+    {
+      "epoch": 0.005921539600296077,
+      "grad_norm": 0.027431325986981392,
+      "learning_rate": 8e-05,
+      "loss": 10.3741,
+      "step": 4
+    },
+    {
+      "epoch": 0.007401924500370096,
+      "grad_norm": 0.028998393565416336,
+      "learning_rate": 0.0001,
+      "loss": 10.3758,
+      "step": 5
+    },
+    {
+      "epoch": 0.008882309400444115,
+      "grad_norm": 0.03407181054353714,
+      "learning_rate": 0.00012,
+      "loss": 10.3745,
+      "step": 6
+    },
+    {
+      "epoch": 0.008882309400444115,
+      "eval_loss": 10.374056816101074,
+      "eval_runtime": 1.2091,
+      "eval_samples_per_second": 235.721,
+      "eval_steps_per_second": 118.274,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 77585448960.0,
+  "total_flos": 155170897920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null