Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c4b073090691334b5a6b829305b229bd63292d3fed53c5bc80b4c00d7c82577
+oid sha256:400a6dea76a8b7d10f7d494639d98d34a388b2ee3181f8c34a0d84c835d92d58
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e45fb58a93b5bdf3fa5fa2a8c09db42e4059ec85751cbcc60714c232b596afb1
+oid sha256:74a1c6bacbde46d2a5a6826b4a32c2e09fbc0a0bd294c80b597dcda3577b865d
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d04ce38a4b1ebe155394d1cb2e43ba46dcd389805a0df7f2671ac2a395b23d6c
+oid sha256:376a84af6354b555ba2fbd8c3fc92d9086d0a9dcf2c9793e8d456dbd561d4eb5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007621392662943909,
+  "epoch": 0.0015242785325887819,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 12.884,
       "eval_steps_per_second": 6.442,
       "step": 10
+    },
+    {
+      "epoch": 0.0008793914611089126,
+      "grad_norm": 0.3528475761413574,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.5036,
+      "step": 15
+    },
+    {
+      "epoch": 0.0011725219481452168,
+      "grad_norm": 0.40145859122276306,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.516,
+      "step": 20
+    },
+    {
+      "epoch": 0.0011725219481452168,
+      "eval_loss": 0.4801919460296631,
+      "eval_runtime": 557.7337,
+      "eval_samples_per_second": 12.877,
+      "eval_steps_per_second": 6.439,
+      "step": 20
+    },
+    {
+      "epoch": 0.001465652435181521,
+      "grad_norm": 0.44575509428977966,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.4756,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2117374014652416.0,
+  "total_flos": 4234748029304832.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null