Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:218c8cf44601c32795abed0ab2628f7678394aa92662230afe1484bca6930b59
+oid sha256:042945f16a17a459d87953399ea1a2abb1b006971581e2320284fd8b4f703685
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64288ec675b5ffa587a7b70c78d2cda495c4b7437141d79a69f823f8b024e34
+oid sha256:84036c912122fcc1929ce921db81001c768bd741955224a2848ab42f700b9f20
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359f88406f363fc6c9eb07a6622f1ae622ffd0fa054e681698b03e8645ebf202
+oid sha256:f81634af63009bf1a378ed0c44c0336f57a044af94ea02f6aaa12848ad1a0599
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0047025628967787446,
+  "epoch": 0.007053844345168116,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,28 @@
       "eval_samples_per_second": 49.254,
       "eval_steps_per_second": 6.16,
       "step": 10
+    },
+    {
+      "epoch": 0.005643075476134493,
+      "grad_norm": 0.6331816911697388,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 1.1578,
+      "step": 12
+    },
+    {
+      "epoch": 0.007053844345168116,
+      "grad_norm": 0.5597560405731201,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.2228,
+      "step": 15
+    },
+    {
+      "epoch": 0.007053844345168116,
+      "eval_loss": 1.157048225402832,
+      "eval_runtime": 72.6624,
+      "eval_samples_per_second": 49.296,
+      "eval_steps_per_second": 6.166,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2133147852472320.0,
+  "total_flos": 3199721778708480.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null