Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae63c87fa352e1881c6b023a32fa8a537469147a2534ed210f1822ff1610e73e
+oid sha256:75aeecb871f23a5d58dae01b83be825430b70915132983f6ba9170a6526a449d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78d682f10d4517fdc9925f7a85bde122f87d71766df7b33ececcd2ef4d1fbf00
+oid sha256:f8c05e34404cafb33833b8727744379f57925c6a3c506d36754b58e0646aa351
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a36b079fde0d50a71846e4012b55dbfb2dd9d8c0de22b0a59c006da6f057b01b
+oid sha256:bc05cd3a98949633cd0945d642fde31aa27434b462cc4feb8ff105332385519f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0002496671105193076,
+  "epoch": 0.00037450066577896136,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 17.368,
       "eval_steps_per_second": 8.685,
       "step": 6
+    },
+    {
+      "epoch": 0.00029127829560585887,
+      "grad_norm": 5.4711151123046875,
+      "learning_rate": 0.00014,
+      "loss": 2.9968,
+      "step": 7
+    },
+    {
+      "epoch": 0.00033288948069241014,
+      "grad_norm": 5.150915145874023,
+      "learning_rate": 0.00016,
+      "loss": 3.0618,
+      "step": 8
+    },
+    {
+      "epoch": 0.00037450066577896136,
+      "grad_norm": 4.605907917022705,
+      "learning_rate": 0.00018,
+      "loss": 2.453,
+      "step": 9
+    },
+    {
+      "epoch": 0.00037450066577896136,
+      "eval_loss": 0.6927347183227539,
+      "eval_runtime": 582.0922,
+      "eval_samples_per_second": 17.384,
+      "eval_steps_per_second": 8.693,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2103204951097344.0,
+  "total_flos": 3154807426646016.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null