Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84abe44504b8e74fc7b4a24dbcf8278ceaa2c95463cccee140a61acc58128e79
+oid sha256:d281ba77a7c19709ff33509b72d143d431829646ed5ba624edb447a350d7b62f
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:369e60a8b0bf5ff3cb695cb28eb43a9681dc4ab9385cbc7ca9000c3de5da979b
+oid sha256:fe393cafac36ec99a030cc8d91682a823892ed135f3c6aa636dee1bed4c64154
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0deda1b281fa205ba4f0c4f67c280971d309fc191532dbb5ef8f5efa66a3e16
+oid sha256:dea7995b1ae614b00c83c2a701da2802a0ff4b8551bbf5102fa6204b6e49ebe7
 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": 0.10741138560687433,
+  "epoch": 0.21482277121374865,
   "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": 6.029,
       "eval_steps_per_second": 3.015,
       "step": 25
+    },
+    {
+      "epoch": 0.11170784103114931,
+      "grad_norm": 20.040693283081055,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 2.8217,
+      "step": 26
+    },
+    {
+      "epoch": 0.11600429645542427,
+      "grad_norm": 8.479001998901367,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.4105,
+      "step": 27
+    },
+    {
+      "epoch": 0.12030075187969924,
+      "grad_norm": 4.354423522949219,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 2.4466,
+      "step": 28
+    },
+    {
+      "epoch": 0.12459720730397422,
+      "grad_norm": 3.0479633808135986,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 2.496,
+      "step": 29
+    },
+    {
+      "epoch": 0.1288936627282492,
+      "grad_norm": 5.260918617248535,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.7696,
+      "step": 30
+    },
+    {
+      "epoch": 0.13319011815252416,
+      "grad_norm": 2.6381261348724365,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.4536,
+      "step": 31
+    },
+    {
+      "epoch": 0.13748657357679914,
+      "grad_norm": 2.3083853721618652,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 2.4325,
+      "step": 32
+    },
+    {
+      "epoch": 0.14178302900107412,
+      "grad_norm": 4.7310791015625,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 2.4458,
+      "step": 33
+    },
+    {
+      "epoch": 0.1460794844253491,
+      "grad_norm": 3.6756527423858643,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 2.5719,
+      "step": 34
+    },
+    {
+      "epoch": 0.15037593984962405,
+      "grad_norm": 2.2964797019958496,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 2.5365,
+      "step": 35
+    },
+    {
+      "epoch": 0.15467239527389903,
+      "grad_norm": 4.085907459259033,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 2.684,
+      "step": 36
+    },
+    {
+      "epoch": 0.158968850698174,
+      "grad_norm": 5.398529052734375,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 2.5946,
+      "step": 37
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 4.9892754554748535,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 2.7752,
+      "step": 38
+    },
+    {
+      "epoch": 0.16756176154672395,
+      "grad_norm": 4.568504810333252,
+      "learning_rate": 5e-05,
+      "loss": 2.5394,
+      "step": 39
+    },
+    {
+      "epoch": 0.17185821697099893,
+      "grad_norm": 5.603278636932373,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 2.3277,
+      "step": 40
+    },
+    {
+      "epoch": 0.1761546723952739,
+      "grad_norm": 5.817256927490234,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 2.7044,
+      "step": 41
+    },
+    {
+      "epoch": 0.18045112781954886,
+      "grad_norm": 5.201894283294678,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.8322,
+      "step": 42
+    },
+    {
+      "epoch": 0.18474758324382384,
+      "grad_norm": 2.171565055847168,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.495,
+      "step": 43
+    },
+    {
+      "epoch": 0.18904403866809882,
+      "grad_norm": 4.212491035461426,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 2.7337,
+      "step": 44
+    },
+    {
+      "epoch": 0.1933404940923738,
+      "grad_norm": 4.5573954582214355,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.6864,
+      "step": 45
+    },
+    {
+      "epoch": 0.19763694951664876,
+      "grad_norm": 7.083897113800049,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 2.9271,
+      "step": 46
+    },
+    {
+      "epoch": 0.20193340494092374,
+      "grad_norm": 5.476693153381348,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 2.7912,
+      "step": 47
+    },
+    {
+      "epoch": 0.20622986036519872,
+      "grad_norm": 2.044529676437378,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.4948,
+      "step": 48
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 4.62539529800415,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 2.4246,
+      "step": 49
+    },
+    {
+      "epoch": 0.21482277121374865,
+      "grad_norm": 8.88616943359375,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 3.1202,
+      "step": 50
+    },
+    {
+      "epoch": 0.21482277121374865,
+      "eval_loss": 2.50577712059021,
+      "eval_runtime": 32.5083,
+      "eval_samples_per_second": 6.029,
+      "eval_steps_per_second": 3.015,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.73005226082304e+16,
+  "total_flos": 7.46010452164608e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null