Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e402e5eab5c23aa11f39d9972826282faed36c93846e2f7b33eed3ab04edcdf
+oid sha256:78a05f32290854cc5c3e51c437a571661fecdfed327a489b210ac45ebb4ac9aa
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a619e3fb5a37cb5f92255e53eec0a3d9ffa190dea8c930fa703195a41aff1415
+oid sha256:06b890163dff2517f61d169c3a37a2479772c0d8d2a189e937d0e851e151e656
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6bf19e75a59ee8c6a96e9c63d30b78c698cbfef05ceb7eb28dd7602d0b1a826
+oid sha256:fea4a6c63434c27a483922b729f3295cf32c5e237d07366009f63d639620f157
 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": 0.021145374449339206,
+  "epoch": 0.03171806167400881,
   "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": 32.102,
       "eval_steps_per_second": 16.051,
       "step": 6
+    },
+    {
+      "epoch": 0.024669603524229075,
+      "grad_norm": 20.36292839050293,
+      "learning_rate": 0.00014,
+      "loss": 3.3894,
+      "step": 7
+    },
+    {
+      "epoch": 0.028193832599118944,
+      "grad_norm": 21.608123779296875,
+      "learning_rate": 0.00016,
+      "loss": 1.8491,
+      "step": 8
+    },
+    {
+      "epoch": 0.03171806167400881,
+      "grad_norm": 10.76959228515625,
+      "learning_rate": 0.00018,
+      "loss": 0.8269,
+      "step": 9
+    },
+    {
+      "epoch": 0.03171806167400881,
+      "eval_loss": 0.6693419814109802,
+      "eval_runtime": 3.7065,
+      "eval_samples_per_second": 32.376,
+      "eval_steps_per_second": 16.188,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1109738548887552.0,
+  "total_flos": 1664607823331328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null