Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91331a6191874d38ebfbd51b64e593bbc31dff414430fe95e3475e72951a863a
+oid sha256:677255549c53250b75e79ccaba7a3dac86c661fff49eaedf1b2b69d55cff549c
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e8b11a214c5fd3481dfaf52a901e8e6b491a49f58b06393b24c6861936e6a90
+oid sha256:10d2d2af12a15acf9a396e316f23f3046391067292e9d303b16fc4f4cc0a467a
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7b14d0c915e2c4063f110f3dbec036a026b529b8820509b2913f154771be18b
+oid sha256:e9ed9626ba6e412f40126198b85320c11d70caab3bee87c19069e3aea6dd4f83
 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": 0.020600858369098713,
+  "epoch": 0.030901287553648068,
   "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": 17.069,
       "eval_steps_per_second": 8.604,
       "step": 6
+    },
+    {
+      "epoch": 0.0240343347639485,
+      "grad_norm": 0.5286383628845215,
+      "learning_rate": 0.00014,
+      "loss": 0.8375,
+      "step": 7
+    },
+    {
+      "epoch": 0.027467811158798282,
+      "grad_norm": 0.6298297643661499,
+      "learning_rate": 0.00016,
+      "loss": 1.0884,
+      "step": 8
+    },
+    {
+      "epoch": 0.030901287553648068,
+      "grad_norm": 0.5216607451438904,
+      "learning_rate": 0.00018,
+      "loss": 0.7053,
+      "step": 9
+    },
+    {
+      "epoch": 0.030901287553648068,
+      "eval_loss": 0.8822326064109802,
+      "eval_runtime": 7.2091,
+      "eval_samples_per_second": 17.062,
+      "eval_steps_per_second": 8.6,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2219477097775104.0,
+  "total_flos": 3329215646662656.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null