Training in progress, epoch 2, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36c4183b3f6ae7f8de61238edc780abaf030dcb3be9b32af3b20cb6c1492fe04
+oid sha256:352aaca1805beff8b3dca9410c6799fba0c5d2ebef2b9843d0cc983b32b85269
 size 146815928

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d22e73536337c711d81d48701cdc1584bca29db7505507292c31dd295916a203
+oid sha256:cef92f4f1cc5379d8df11ef1f05734dc3bf1aa7ad0721e7ac4489c256d8e4d2c
 size 74680890

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6968d40cf0c71d4e3ee9bf2859204537af78d1178eb0820c06fa4101d008adb9
+oid sha256:e7c2b9c568ef9032dbbe63731fc47d6288db403b82ba8fc7fe6f0e4bbf73753d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd0ba268c49e105d03b88e15b67f1fa9af614b44c781f77e09e8b26a00bd96e7
+oid sha256:0a3d6766978e7b23f56ff8b154d43c7f45dbb5076c006b6787ac495916d5ce0c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 350,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,42 @@
       "eval_samples_per_second": 2.109,
       "eval_steps_per_second": 0.527,
       "step": 350
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 1.8639676570892334,
+      "learning_rate": 0.00016,
+      "loss": 0.5839,
+      "step": 400
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 1.6524343490600586,
+      "learning_rate": 0.0002,
+      "loss": 0.4143,
+      "step": 500
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 1.1418366432189941,
+      "learning_rate": 0.00019333333333333333,
+      "loss": 0.3445,
+      "step": 600
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0962567329406738,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 0.3012,
+      "step": 700
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.2971023917198181,
+      "eval_runtime": 331.597,
+      "eval_samples_per_second": 2.111,
+      "eval_steps_per_second": 0.528,
+      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -55,7 +91,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8531255003971584.0,
+  "total_flos": 1.7093931183374336e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null