Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5129ec00a512586035339a5bf0f4bfb5de837df7d04111fea9b183b280bf0d1d
+oid sha256:2644d5ee61e94ad63fbbc3e485c72e9f50f0f70254241b2ea4da79a07e4f139d
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c627f0adf6c045baa801bd78ebaa3c1395c4e66a4ec1f3945591a4758a0ec84
+oid sha256:889f3b0bf64a6e2f6d92906c9ed29c8614a6602590c5b4b213b276bfdbdaab45
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c54966f2465e62f3f23221c1b18d8d6c1829302b329b674439c498e34e1b28ba
+oid sha256:c8f9bfbb25b5742af971410f7969204872224492d0748212c97b7e3aec33a144
 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": 0.0003398374444224179,
+  "epoch": 0.0006796748888448359,
   "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": 295.796,
       "eval_steps_per_second": 147.938,
       "step": 3
+    },
+    {
+      "epoch": 0.0004531165925632239,
+      "grad_norm": 0.04086960479617119,
+      "learning_rate": 8e-05,
+      "loss": 10.3717,
+      "step": 4
+    },
+    {
+      "epoch": 0.0005663957407040299,
+      "grad_norm": 0.03967590257525444,
+      "learning_rate": 0.0001,
+      "loss": 10.3784,
+      "step": 5
+    },
+    {
+      "epoch": 0.0006796748888448359,
+      "grad_norm": 0.046869322657585144,
+      "learning_rate": 0.00012,
+      "loss": 10.3747,
+      "step": 6
+    },
+    {
+      "epoch": 0.0006796748888448359,
+      "eval_loss": 10.371750831604004,
+      "eval_runtime": 12.7077,
+      "eval_samples_per_second": 292.5,
+      "eval_steps_per_second": 146.289,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 71119994880.0,
+  "total_flos": 139007262720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null