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:a211f0484503b27954793d3baeacb90a829a429b31f056754853bb7c9013d74b
+oid sha256:dde1f541075528a8656dc374c75feda38796f86a82a24bd96bb3212bc495bc31
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15bf7d462fec9d23191eb5af705dc1df09e4183ab83ed8246aeec8e47de9e81c
+oid sha256:0b53d32da29ba12bd7822a78974e90af504c8eb38da23569fa23d719d9071e9c
 size 864785974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcbe00f971e9d5e81c19215785044c6a8c173df1974b22b9926999d4b2581d8b
+oid sha256:4187fc1d152ba9faf65a5780677918fddb5070f2298188d0c986ef27e6742016
 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": 0.23837902264600716,
+  "epoch": 0.4767580452920143,
   "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": 1.622,
       "eval_steps_per_second": 0.82,
       "step": 25
+    },
+    {
+      "epoch": 0.24791418355184744,
+      "grad_norm": 0.4809877872467041,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.2921,
+      "step": 26
+    },
+    {
+      "epoch": 0.25744934445768775,
+      "grad_norm": 1.3561242818832397,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.1493,
+      "step": 27
+    },
+    {
+      "epoch": 0.266984505363528,
+      "grad_norm": 1.378612756729126,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.1205,
+      "step": 28
+    },
+    {
+      "epoch": 0.2765196662693683,
+      "grad_norm": 1.3110326528549194,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.09,
+      "step": 29
+    },
+    {
+      "epoch": 0.2860548271752086,
+      "grad_norm": 0.8067518472671509,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.035,
+      "step": 30
+    },
+    {
+      "epoch": 0.29558998808104886,
+      "grad_norm": 30.427331924438477,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.3727,
+      "step": 31
+    },
+    {
+      "epoch": 0.30512514898688914,
+      "grad_norm": 30.505556106567383,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 2.8594,
+      "step": 32
+    },
+    {
+      "epoch": 0.3146603098927294,
+      "grad_norm": 26.016315460205078,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 2.531,
+      "step": 33
+    },
+    {
+      "epoch": 0.32419547079856975,
+      "grad_norm": 14.183924674987793,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 1.1554,
+      "step": 34
+    },
+    {
+      "epoch": 0.33373063170441003,
+      "grad_norm": 1.8867197036743164,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.2323,
+      "step": 35
+    },
+    {
+      "epoch": 0.3432657926102503,
+      "grad_norm": 1.2031322717666626,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.2414,
+      "step": 36
+    },
+    {
+      "epoch": 0.3528009535160906,
+      "grad_norm": 1.523146390914917,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.2678,
+      "step": 37
+    },
+    {
+      "epoch": 0.36233611442193087,
+      "grad_norm": 1.5239652395248413,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.2312,
+      "step": 38
+    },
+    {
+      "epoch": 0.37187127532777114,
+      "grad_norm": 1.0078612565994263,
+      "learning_rate": 5e-05,
+      "loss": 0.1885,
+      "step": 39
+    },
+    {
+      "epoch": 0.3814064362336114,
+      "grad_norm": 4.037468433380127,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.4962,
+      "step": 40
+    },
+    {
+      "epoch": 0.3909415971394517,
+      "grad_norm": 2.556730031967163,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.4065,
+      "step": 41
+    },
+    {
+      "epoch": 0.40047675804529204,
+      "grad_norm": 1.4753957986831665,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3817,
+      "step": 42
+    },
+    {
+      "epoch": 0.4100119189511323,
+      "grad_norm": 1.1868329048156738,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.2182,
+      "step": 43
+    },
+    {
+      "epoch": 0.4195470798569726,
+      "grad_norm": 0.9121273159980774,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.2606,
+      "step": 44
+    },
+    {
+      "epoch": 0.42908224076281287,
+      "grad_norm": 0.551138162612915,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2798,
+      "step": 45
+    },
+    {
+      "epoch": 0.43861740166865315,
+      "grad_norm": 0.5170517563819885,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.2307,
+      "step": 46
+    },
+    {
+      "epoch": 0.44815256257449343,
+      "grad_norm": 0.3968268036842346,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.2303,
+      "step": 47
+    },
+    {
+      "epoch": 0.4576877234803337,
+      "grad_norm": 0.3745101988315582,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.2629,
+      "step": 48
+    },
+    {
+      "epoch": 0.46722288438617404,
+      "grad_norm": 0.7609822750091553,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.2946,
+      "step": 49
+    },
+    {
+      "epoch": 0.4767580452920143,
+      "grad_norm": 0.4893784523010254,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.2266,
+      "step": 50
+    },
+    {
+      "epoch": 0.4767580452920143,
+      "eval_loss": 0.2717249393463135,
+      "eval_runtime": 54.8636,
+      "eval_samples_per_second": 1.622,
+      "eval_steps_per_second": 0.82,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.49161310093312e+16,
+  "total_flos": 1.0921056996950016e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null