Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12aaaee2a037a1af85ecc1881328b9100f4098b466e3ff68840b22783375140f
+oid sha256:f30960e60996a50fa5fdb4957a646f26a039e633cbfd6afdcde9f61f0413e06f
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46996d9faace41733b7959f929307a0330c52ba264e86103d5b8fc5668c334e0
+oid sha256:7b5021af618caa6e613343ae3b2379fa4b9b4641c7931d8fb35c3e58b4ab4ffa
 size 9568884

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": 0.05809731299927379,
+  "epoch": 0.08714596949891068,
   "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": 69.385,
       "eval_steps_per_second": 34.693,
       "step": 10
+    },
+    {
+      "epoch": 0.06390704429920116,
+      "grad_norm": 2.665182113647461,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.9545,
+      "step": 11
+    },
+    {
+      "epoch": 0.06971677559912855,
+      "grad_norm": 2.2438454627990723,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.863,
+      "step": 12
+    },
+    {
+      "epoch": 0.07552650689905592,
+      "grad_norm": 2.2425379753112793,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.755,
+      "step": 13
+    },
+    {
+      "epoch": 0.0813362381989833,
+      "grad_norm": 1.502351999282837,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.7284,
+      "step": 14
+    },
+    {
+      "epoch": 0.08714596949891068,
+      "grad_norm": 1.436643123626709,
+      "learning_rate": 5e-05,
+      "loss": 0.5585,
+      "step": 15
+    },
+    {
+      "epoch": 0.08714596949891068,
+      "eval_loss": 0.6648338437080383,
+      "eval_runtime": 4.1764,
+      "eval_samples_per_second": 69.437,
+      "eval_steps_per_second": 34.719,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 356152655216640.0,
+  "total_flos": 534228982824960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null