Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b23eac600e2d9d1425bb5889653d3aafcc1d176a87741d192e34052906dfcb6
+oid sha256:0c260e5c0e8276d42d03a9a162c85270b7e1958064ce937c1d144c5375f9e59c
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fad1001ac4d7d01bd8c5402d600220534aa6338d03793d051c3cff9735571ac7
+oid sha256:a844b2abc40a617542b6e0dcb797905924b76e181ce5648f7b5dc0134abb898e
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621b60809732920aa471939cce99ce40c4b197b94cc928e040d333b1c2d6b80f
+oid sha256:bc4bb0b5e6b7c80ecb411483c99281e80a04c0d48447d5eb2f3553b64ba3373a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
+oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.029697315819531698,
+  "epoch": 0.04454597372929754,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 17.038,
       "eval_steps_per_second": 8.542,
       "step": 26
+    },
+    {
+      "epoch": 0.03083952027412907,
+      "grad_norm": 1.4825445413589478,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 1.4761,
+      "step": 27
+    },
+    {
+      "epoch": 0.03198172472872644,
+      "grad_norm": 1.2867043018341064,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 2.1147,
+      "step": 28
+    },
+    {
+      "epoch": 0.03312392918332382,
+      "grad_norm": 1.2437233924865723,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 2.1772,
+      "step": 29
+    },
+    {
+      "epoch": 0.034266133637921185,
+      "grad_norm": 1.182763934135437,
+      "learning_rate": 0.0001,
+      "loss": 2.0657,
+      "step": 30
+    },
+    {
+      "epoch": 0.03540833809251856,
+      "grad_norm": 1.4356260299682617,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 1.8824,
+      "step": 31
+    },
+    {
+      "epoch": 0.036550542547115934,
+      "grad_norm": 1.2100356817245483,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.6299,
+      "step": 32
+    },
+    {
+      "epoch": 0.03769274700171331,
+      "grad_norm": 1.505204677581787,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 2.0104,
+      "step": 33
+    },
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 1.2709004878997803,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.8537,
+      "step": 34
+    },
+    {
+      "epoch": 0.03997715591090805,
+      "grad_norm": 1.2521007061004639,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 2.085,
+      "step": 35
+    },
+    {
+      "epoch": 0.041119360365505425,
+      "grad_norm": 1.5052094459533691,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 1.8497,
+      "step": 36
+    },
+    {
+      "epoch": 0.0422615648201028,
+      "grad_norm": 1.502581238746643,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 2.3156,
+      "step": 37
+    },
+    {
+      "epoch": 0.043403769274700174,
+      "grad_norm": 1.0777575969696045,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.793,
+      "step": 38
+    },
+    {
+      "epoch": 0.04454597372929754,
+      "grad_norm": 2.488421678543091,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 1.7356,
+      "step": 39
+    },
+    {
+      "epoch": 0.04454597372929754,
+      "eval_loss": 0.5092501640319824,
+      "eval_runtime": 21.614,
+      "eval_samples_per_second": 17.072,
+      "eval_steps_per_second": 8.559,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9261206093168640.0,
+  "total_flos": 1.401054255120384e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null