Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5c9d025d9e659c4712f67c78ffb92be94fbc17ecb80166e34316885db7e5e85
+oid sha256:3b2fee3e15feab3a0047553eccce557d475a1dcb3ac4d45283ac34edfe334ed6
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4c71f8c87f2e4f9ae52bfede5ed605df323f03ad2e7c89bc9b83b553701865
+oid sha256:5038b2411afe299e69ebd276ab86120a5adb69c15d1c241b24e8c29ceeca4ee6
 size 180543866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a070fa9b4f53831b788fe09eb328c29fb2c78b5e115a4240d3d982b96430fb4
+oid sha256:566d560e6b36fe4550a5847fef06f89ecba2d66c364128fc9977de8e9e411a5e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020764119601328904,
+  "epoch": 0.04152823920265781,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 14.188,
       "eval_steps_per_second": 7.094,
       "step": 25
+    },
+    {
+      "epoch": 0.02159468438538206,
+      "grad_norm": 1.8611646890640259,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 1.6921,
+      "step": 26
+    },
+    {
+      "epoch": 0.022425249169435217,
+      "grad_norm": 1.7114734649658203,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.5121,
+      "step": 27
+    },
+    {
+      "epoch": 0.023255813953488372,
+      "grad_norm": 1.9501327276229858,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 2.0156,
+      "step": 28
+    },
+    {
+      "epoch": 0.02408637873754153,
+      "grad_norm": 1.7911945581436157,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 1.5041,
+      "step": 29
+    },
+    {
+      "epoch": 0.024916943521594685,
+      "grad_norm": 1.709389090538025,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.6483,
+      "step": 30
+    },
+    {
+      "epoch": 0.02574750830564784,
+      "grad_norm": 1.8848737478256226,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.8492,
+      "step": 31
+    },
+    {
+      "epoch": 0.026578073089700997,
+      "grad_norm": 2.078946113586426,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 1.6023,
+      "step": 32
+    },
+    {
+      "epoch": 0.027408637873754152,
+      "grad_norm": 2.286283254623413,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 1.7772,
+      "step": 33
+    },
+    {
+      "epoch": 0.02823920265780731,
+      "grad_norm": 2.291384696960449,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 1.9919,
+      "step": 34
+    },
+    {
+      "epoch": 0.029069767441860465,
+      "grad_norm": 2.2174739837646484,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.8295,
+      "step": 35
+    },
+    {
+      "epoch": 0.029900332225913623,
+      "grad_norm": 2.378859758377075,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 1.8642,
+      "step": 36
+    },
+    {
+      "epoch": 0.030730897009966777,
+      "grad_norm": 2.1495234966278076,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 2.3204,
+      "step": 37
+    },
+    {
+      "epoch": 0.03156146179401993,
+      "grad_norm": 2.106130599975586,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 1.7387,
+      "step": 38
+    },
+    {
+      "epoch": 0.03239202657807309,
+      "grad_norm": 2.0906083583831787,
+      "learning_rate": 5e-05,
+      "loss": 1.9952,
+      "step": 39
+    },
+    {
+      "epoch": 0.03322259136212625,
+      "grad_norm": 2.5236432552337646,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 2.3975,
+      "step": 40
+    },
+    {
+      "epoch": 0.0340531561461794,
+      "grad_norm": 2.412330150604248,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 2.3625,
+      "step": 41
+    },
+    {
+      "epoch": 0.03488372093023256,
+      "grad_norm": 2.1376240253448486,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.1484,
+      "step": 42
+    },
+    {
+      "epoch": 0.03571428571428571,
+      "grad_norm": 2.4796907901763916,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.8789,
+      "step": 43
+    },
+    {
+      "epoch": 0.036544850498338874,
+      "grad_norm": 2.7524349689483643,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 2.6193,
+      "step": 44
+    },
+    {
+      "epoch": 0.03737541528239203,
+      "grad_norm": 3.215737819671631,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.7779,
+      "step": 45
+    },
+    {
+      "epoch": 0.03820598006644518,
+      "grad_norm": 3.4973068237304688,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 2.6296,
+      "step": 46
+    },
+    {
+      "epoch": 0.03903654485049834,
+      "grad_norm": 3.1748504638671875,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 2.3609,
+      "step": 47
+    },
+    {
+      "epoch": 0.03986710963455149,
+      "grad_norm": 3.053208112716675,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.0583,
+      "step": 48
+    },
+    {
+      "epoch": 0.040697674418604654,
+      "grad_norm": 4.208493232727051,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 2.95,
+      "step": 49
+    },
+    {
+      "epoch": 0.04152823920265781,
+      "grad_norm": 3.1799519062042236,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 3.212,
+      "step": 50
+    },
+    {
+      "epoch": 0.04152823920265781,
+      "eval_loss": 1.978314757347107,
+      "eval_runtime": 71.6979,
+      "eval_samples_per_second": 14.143,
+      "eval_steps_per_second": 7.071,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5138718822236160.0,
+  "total_flos": 1.003273674817536e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null