Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36782ed6d4c9968c620e2246c4d19cb5d4f958e78ba56904cf68ab02980c7474
+oid sha256:e39c0d6c258a59a72f139a2611f470e17454f6a513d90eeeea23c3848ff9d72a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa3502774ac0333793c32421fcccd2cf9f9ff5f5a4fc537c4e0c17a4b140d0f2
+oid sha256:3e9581944951df25a175ca1528cbe2dfb8c38b1dcd06adc624d02a870c055af6
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6011dbc1beaf916a24aa0692a7ad3787fe62f4d3127d9859b27643438838594d
+oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.029973772948669913,
+  "epoch": 0.04496065942300487,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 41.075,
       "eval_steps_per_second": 20.538,
       "step": 10
+    },
+    {
+      "epoch": 0.032971150243536904,
+      "grad_norm": 2.882046937942505,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.5317,
+      "step": 11
+    },
+    {
+      "epoch": 0.0359685275384039,
+      "grad_norm": 1.854430913925171,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.4635,
+      "step": 12
+    },
+    {
+      "epoch": 0.038965904833270885,
+      "grad_norm": 1.4817869663238525,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.2889,
+      "step": 13
+    },
+    {
+      "epoch": 0.04196328212813788,
+      "grad_norm": 1.171612024307251,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.1823,
+      "step": 14
+    },
+    {
+      "epoch": 0.04496065942300487,
+      "grad_norm": 1.0793206691741943,
+      "learning_rate": 5e-05,
+      "loss": 0.1778,
+      "step": 15
+    },
+    {
+      "epoch": 0.04496065942300487,
+      "eval_loss": 0.1316353678703308,
+      "eval_runtime": 13.6689,
+      "eval_samples_per_second": 41.115,
+      "eval_steps_per_second": 20.558,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7444496098787328.0,
+  "total_flos": 1.1143624595079168e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null