Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f8befd50d5fbdc7ccaf456f1ab0bf254a92cf2a2b42b2eec453732c497424c0
+oid sha256:a8d09d8e582a20ae11507aeebc9a7136cc96ac9f8a3d710147005b93487aa7fd
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b704e552235f49cda42e464c052fcbff156f28d457a3e3c134985d5191150d87
+oid sha256:7ceb59de528bbb3c4cf8763991894defe2944764bc2e03bb6bed8b1a02944391
 size 13685516

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": 0.0013423381853265657,
+  "epoch": 0.0020135072779898485,
   "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": 126.882,
       "eval_steps_per_second": 63.446,
       "step": 10
+    },
+    {
+      "epoch": 0.0014765720038592222,
+      "grad_norm": 9.79337215423584,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 3.3908,
+      "step": 11
+    },
+    {
+      "epoch": 0.0016108058223918789,
+      "grad_norm": 6.4604644775390625,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 3.3314,
+      "step": 12
+    },
+    {
+      "epoch": 0.0017450396409245353,
+      "grad_norm": 15.380472183227539,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.8384,
+      "step": 13
+    },
+    {
+      "epoch": 0.001879273459457192,
+      "grad_norm": 4.442010402679443,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.7271,
+      "step": 14
+    },
+    {
+      "epoch": 0.0020135072779898485,
+      "grad_norm": 4.581469535827637,
+      "learning_rate": 5e-05,
+      "loss": 2.6547,
+      "step": 15
+    },
+    {
+      "epoch": 0.0020135072779898485,
+      "eval_loss": 2.4406354427337646,
+      "eval_runtime": 98.7192,
+      "eval_samples_per_second": 127.098,
+      "eval_steps_per_second": 63.554,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1023167913000960.0,
+  "total_flos": 1534751869501440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null