Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:402ccb399f4ad76ed63633dd6467aa70f50cfecbb8b8d2b860a95f9aa38e54f6
+oid sha256:823b261ef99b1e191a872a1cbd0e66bf08cb406a99a6b58f8f72266b82aac2f3
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4abf6ce2e5cf82ccdb317b4095e669e17fff95526bf1d3025d49b4d643747e3f
+oid sha256:3908c845b321034463b1730a374291100e15b1dff0852e4cbedc713d30402c95
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d2d6bc08ef3abdbd8d1e9ebf2fe9eda911a26db8affa656809086ee10975bba
+oid sha256:9f22ee2bd42680b5f198191658fb24f22c66fd0968ab26c6e7ce687248687a73
 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": 0.0456140350877193,
+  "epoch": 0.06842105263157895,
   "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": 56.125,
       "eval_steps_per_second": 28.062,
       "step": 26
+    },
+    {
+      "epoch": 0.04736842105263158,
+      "grad_norm": 6.506723880767822,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 6.5923,
+      "step": 27
+    },
+    {
+      "epoch": 0.04912280701754386,
+      "grad_norm": 5.621894359588623,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 6.1451,
+      "step": 28
+    },
+    {
+      "epoch": 0.05087719298245614,
+      "grad_norm": 6.360438346862793,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 7.1938,
+      "step": 29
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 6.532863616943359,
+      "learning_rate": 0.0001,
+      "loss": 6.9762,
+      "step": 30
+    },
+    {
+      "epoch": 0.054385964912280704,
+      "grad_norm": 6.711584091186523,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 7.1213,
+      "step": 31
+    },
+    {
+      "epoch": 0.056140350877192984,
+      "grad_norm": 6.394320487976074,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 7.1146,
+      "step": 32
+    },
+    {
+      "epoch": 0.05789473684210526,
+      "grad_norm": 6.20180082321167,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 7.1802,
+      "step": 33
+    },
+    {
+      "epoch": 0.05964912280701754,
+      "grad_norm": 6.715718746185303,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 7.0011,
+      "step": 34
+    },
+    {
+      "epoch": 0.06140350877192982,
+      "grad_norm": 6.306797027587891,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 7.1968,
+      "step": 35
+    },
+    {
+      "epoch": 0.06315789473684211,
+      "grad_norm": 7.334612846374512,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 6.2764,
+      "step": 36
+    },
+    {
+      "epoch": 0.06491228070175438,
+      "grad_norm": 6.493529796600342,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 6.5648,
+      "step": 37
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 5.998836994171143,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.7859,
+      "step": 38
+    },
+    {
+      "epoch": 0.06842105263157895,
+      "grad_norm": 6.2978925704956055,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 6.1908,
+      "step": 39
+    },
+    {
+      "epoch": 0.06842105263157895,
+      "eval_loss": 1.6301758289337158,
+      "eval_runtime": 4.3085,
+      "eval_samples_per_second": 55.704,
+      "eval_steps_per_second": 27.852,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1697668241817600.0,
+  "total_flos": 2546502362726400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null