Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:602013ae87516812205f0ff9a7f72b136876fd4928114777f8049f7b9aec5d98
+oid sha256:37712096092d8d16805f1851c0cb5487c1de2a7e290293d6cb6687f076ec6366
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f9feed44f4cb2419614ccf223f5ac83b625a148c67b92e9b20111e9f28c32b1
+oid sha256:76ca88a3291a3f98680748610a53429c8f18e90fc183970e1796d919e06c73aa
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a7eaefb7c8d3ff9aefbd8df87422c4e9c44a463b8ccfc3f0db11252f9faa01b
+oid sha256:6c56893ec02e2f131eda7c55d301561be28b6d224e001718380f1874157a5126
 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": 0.03955500618046971,
+  "epoch": 0.059332509270704575,
   "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": 2.77,
       "eval_steps_per_second": 1.385,
       "step": 10
+    },
+    {
+      "epoch": 0.04351050679851669,
+      "grad_norm": 72.24517059326172,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 86.7828,
+      "step": 11
+    },
+    {
+      "epoch": 0.047466007416563656,
+      "grad_norm": 75.16802215576172,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 90.0533,
+      "step": 12
+    },
+    {
+      "epoch": 0.05142150803461063,
+      "grad_norm": 66.52326965332031,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 85.0806,
+      "step": 13
+    },
+    {
+      "epoch": 0.0553770086526576,
+      "grad_norm": 68.9215316772461,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 77.0213,
+      "step": 14
+    },
+    {
+      "epoch": 0.059332509270704575,
+      "grad_norm": 59.450138092041016,
+      "learning_rate": 5e-05,
+      "loss": 75.1714,
+      "step": 15
+    },
+    {
+      "epoch": 0.059332509270704575,
+      "eval_loss": 2.192617893218994,
+      "eval_runtime": 307.582,
+      "eval_samples_per_second": 2.77,
+      "eval_steps_per_second": 1.385,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0455331230449664e+17,
+  "total_flos": 1.5682996845674496e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null