Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:127431fb38414cc1859888cab1f7d66c3901f7f566ce75a862dee0efd2646920
+oid sha256:1af7c68dddd4c07b21d5d7ebfe7305d018c2f79fb8f3e923f9992c4dc5028113
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7686d0604c9c865202a88ea90005b9a55cd16730fa77e4b6b2cd92bad0f8a695
+oid sha256:777463137d179646b3dcdc335fc1e392a657cbbd1967b01b54cea0bbabe08d2f
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:400c3c9ddfa8d89702dcba532a94ca20c91dded7a432307b52a723bd7474fb3c
+oid sha256:5631bbf02b26fe187968a013bbddf8fd4c860685f275c830320a8cd4afa18d26
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5c86a5f1be208ec785ba281b2e5648089217f5716d3481d0becb6360f66da60
+oid sha256:c05db228c582523f2484f96646741880104bd1f199b26c4fb4dad8d90c7b8232
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22a6e6a0b2784c7e2a9fa2d84da5a62a9f8cb07ce793f7ae78e83f3f18f8cb85
+oid sha256:ac599fff4b26ed2f8aaa3f64038b795f8035d5e4d74e62f4a3c0c4e718607220
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5682574916759157,
+  "epoch": 0.8523862375138734,
   "eval_steps": 8,
-  "global_step": 16,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -143,6 +143,70 @@
       "eval_samples_per_second": 10.788,
       "eval_steps_per_second": 2.725,
       "step": 16
+    },
+    {
+      "epoch": 0.6037735849056604,
+      "grad_norm": 0.23342889547348022,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.8903,
+      "step": 17
+    },
+    {
+      "epoch": 0.6392896781354052,
+      "grad_norm": 0.21479082107543945,
+      "learning_rate": 3.5659838364445505e-05,
+      "loss": 0.9049,
+      "step": 18
+    },
+    {
+      "epoch": 0.6748057713651499,
+      "grad_norm": 0.2083897590637207,
+      "learning_rate": 3.019601169804216e-05,
+      "loss": 0.9096,
+      "step": 19
+    },
+    {
+      "epoch": 0.7103218645948945,
+      "grad_norm": 0.2214074432849884,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9017,
+      "step": 20
+    },
+    {
+      "epoch": 0.7458379578246392,
+      "grad_norm": 0.21316947042942047,
+      "learning_rate": 2.0142070414860704e-05,
+      "loss": 0.8555,
+      "step": 21
+    },
+    {
+      "epoch": 0.781354051054384,
+      "grad_norm": 0.19444766640663147,
+      "learning_rate": 1.5687918106563326e-05,
+      "loss": 0.8838,
+      "step": 22
+    },
+    {
+      "epoch": 0.8168701442841287,
+      "grad_norm": 0.24460318684577942,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.9097,
+      "step": 23
+    },
+    {
+      "epoch": 0.8523862375138734,
+      "grad_norm": 0.20731952786445618,
+      "learning_rate": 8.225609429353187e-06,
+      "loss": 0.8475,
+      "step": 24
+    },
+    {
+      "epoch": 0.8523862375138734,
+      "eval_loss": 0.9121983647346497,
+      "eval_runtime": 17.6276,
+      "eval_samples_per_second": 10.779,
+      "eval_steps_per_second": 2.723,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -162,7 +226,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.798462891829494e+17,
+  "total_flos": 5.6976943377442406e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null