Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01006bc04cf644c4a19835b0a939d48ffe913d45a0758d78f6312c6b90f4604d
+oid sha256:0aac0658232c5c92bca73f4a88889f22b92b298916261c076026e27ee13f910e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebf28f1e369d1b6504685edbd02f3cac6d25951f3c2c61d9f862929d3c20977d
+oid sha256:00660cc7836a1d12e458523f72fe790c385d7c621fcc3e8ddb93ce103fe34564
 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": 0.034371643394199784,
+  "epoch": 0.05155746509129968,
   "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": 18.697,
       "eval_steps_per_second": 9.349,
       "step": 10
+    },
+    {
+      "epoch": 0.03780880773361976,
+      "grad_norm": 0.857118546962738,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.6361,
+      "step": 11
+    },
+    {
+      "epoch": 0.04124597207303974,
+      "grad_norm": 1.2428054809570312,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.567,
+      "step": 12
+    },
+    {
+      "epoch": 0.04468313641245972,
+      "grad_norm": 1.1504372358322144,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.3349,
+      "step": 13
+    },
+    {
+      "epoch": 0.0481203007518797,
+      "grad_norm": 1.156445860862732,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.4002,
+      "step": 14
+    },
+    {
+      "epoch": 0.05155746509129968,
+      "grad_norm": 0.9205731153488159,
+      "learning_rate": 5e-05,
+      "loss": 2.3525,
+      "step": 15
+    },
+    {
+      "epoch": 0.05155746509129968,
+      "eval_loss": 2.407013416290283,
+      "eval_runtime": 37.4382,
+      "eval_samples_per_second": 13.088,
+      "eval_steps_per_second": 6.544,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7398256992583680.0,
+  "total_flos": 1.109738548887552e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null