Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39b6c9c29df9c2ac9c5285c32391e09cfbc72d7f70a2656e0115b2ef96a04e8d
+oid sha256:f205188dff42985227d31f6aac72d0ae305c1323e80bbdeea9109c554d0a2515
 size 81576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be4113e44bbcd932c38d490379e5a67d31a173c54a336f1ab32996b8bb1f60dc
+oid sha256:92e581caa11338fb46cfe658131b1ceaa112775feddab6b604064a612db02246
 size 173094

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": 0.17718715393134,
+  "epoch": 0.26578073089701,
   "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": 157.588,
       "eval_steps_per_second": 79.623,
       "step": 10
+    },
+    {
+      "epoch": 0.19490586932447398,
+      "grad_norm": 0.12249582260847092,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 10.8356,
+      "step": 11
+    },
+    {
+      "epoch": 0.21262458471760798,
+      "grad_norm": 0.13018162548542023,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.8313,
+      "step": 12
+    },
+    {
+      "epoch": 0.23034330011074197,
+      "grad_norm": 0.11912107467651367,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 10.8301,
+      "step": 13
+    },
+    {
+      "epoch": 0.24806201550387597,
+      "grad_norm": 0.11177022755146027,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.8316,
+      "step": 14
+    },
+    {
+      "epoch": 0.26578073089701,
+      "grad_norm": 0.13372187316417694,
+      "learning_rate": 5e-05,
+      "loss": 10.8337,
+      "step": 15
+    },
+    {
+      "epoch": 0.26578073089701,
+      "eval_loss": 10.833840370178223,
+      "eval_runtime": 0.6893,
+      "eval_samples_per_second": 137.818,
+      "eval_steps_per_second": 69.635,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3322197835776.0,
+  "total_flos": 4962789359616.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null