Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c6dec7a09f866490c070952c80d1eae0da3944936d8142a305986d38ea4f369
+oid sha256:7eabac952144362e06e5038d22466558ecfc80b1c3460d48ad53cdedadbc92ef
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebefd5a4b2f2e7334933eade895e777f7386020e8121e871cb3022882a1538b5
+oid sha256:65f15680ec5d975078f2eab9b86ba0790c3f2779737ea0dbc67e51f7cde46cab
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:760b3cc5c54425216789bc22796c36c6292e4beb44015aabaf5769440b06d5c4
+oid sha256:b466971bc56e50d45ed53ec8544dcc547c522ab03e3c19ab6c40616db98b9af2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b12f644dca975aafa7cd4cb8ce5e2b576382360a37463a3cc5d512a9fe53213d
+oid sha256:a1996614c6c53967c1177fd38254c7aeb2afcca06720e7eecf62b90cd631403c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2597402597402597,
+  "epoch": 0.5194805194805194,
   "eval_steps": 15,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 4.439,
       "eval_steps_per_second": 0.595,
       "step": 15
+    },
+    {
+      "epoch": 0.3116883116883117,
+      "grad_norm": 0.7993184924125671,
+      "learning_rate": 9.940682350363912e-05,
+      "loss": 2.5783,
+      "step": 18
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.88717120885849,
+      "learning_rate": 9.888050389939172e-05,
+      "loss": 3.0288,
+      "step": 21
+    },
+    {
+      "epoch": 0.4155844155844156,
+      "grad_norm": 0.9446913003921509,
+      "learning_rate": 9.819081075450014e-05,
+      "loss": 2.6752,
+      "step": 24
+    },
+    {
+      "epoch": 0.4675324675324675,
+      "grad_norm": 0.7598215937614441,
+      "learning_rate": 9.734004923364257e-05,
+      "loss": 2.6636,
+      "step": 27
+    },
+    {
+      "epoch": 0.5194805194805194,
+      "grad_norm": 0.9138664603233337,
+      "learning_rate": 9.63310628410961e-05,
+      "loss": 2.6451,
+      "step": 30
+    },
+    {
+      "epoch": 0.5194805194805194,
+      "eval_loss": 0.6947051286697388,
+      "eval_runtime": 21.8569,
+      "eval_samples_per_second": 4.438,
+      "eval_steps_per_second": 0.595,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.72809336815616e+16,
+  "total_flos": 1.545618673631232e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null