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:d887c49bd21d7268ead8cbd4f9fcedfd98a065b956ed62fddbd683e3991d86f6
+oid sha256:89b6425fc6e5f3cd8e274e5c0eef41d1c89d5694aeecbbed521cbcc7d1342c24
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c90680251477a9c8a59bc6fb035b11d19e5f5ed7ce05459458a65dd72475b38
+oid sha256:3623ca08a34d444dd74e80c13da02de0f4fc0f4968aeb3dd85deebe07dd3e0c0
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43c7abc92a27b0b273f741dae9c7618464e891c61e90ac22845483a90f2b6a69
+oid sha256:026030288cd601691b26a9dd3addc963d8372e0cdb3ae5ae397bb1e558a3e4d2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cef7bf070e527a9b5896b7711e9e6af634052f75dbe8f4acb6da29f40d856bc6
+oid sha256:8d8615f1aeccd0f9873fc0cf2c0322fde20ac202421c015654a471730a5fa755
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08833922261484099,
+  "epoch": 0.17667844522968199,
   "eval_steps": 9,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -206,6 +206,205 @@
       "learning_rate": 1.866025403784439e-05,
       "loss": 4.1044,
       "step": 25
+    },
+    {
+      "epoch": 0.09187279151943463,
+      "grad_norm": 3.945117712020874,
+      "learning_rate": 1.848048096156426e-05,
+      "loss": 4.1434,
+      "step": 26
+    },
+    {
+      "epoch": 0.09540636042402827,
+      "grad_norm": 3.6443867683410645,
+      "learning_rate": 1.8290375725550417e-05,
+      "loss": 4.0989,
+      "step": 27
+    },
+    {
+      "epoch": 0.09540636042402827,
+      "eval_loss": 3.9746689796447754,
+      "eval_runtime": 7.1709,
+      "eval_samples_per_second": 33.329,
+      "eval_steps_per_second": 4.184,
+      "step": 27
+    },
+    {
+      "epoch": 0.0989399293286219,
+      "grad_norm": 3.7102622985839844,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 4.301,
+      "step": 28
+    },
+    {
+      "epoch": 0.10247349823321555,
+      "grad_norm": 3.6173665523529053,
+      "learning_rate": 1.788010753606722e-05,
+      "loss": 4.2593,
+      "step": 29
+    },
+    {
+      "epoch": 0.10600706713780919,
+      "grad_norm": 4.246015548706055,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 4.1935,
+      "step": 30
+    },
+    {
+      "epoch": 0.10954063604240283,
+      "grad_norm": 4.163142681121826,
+      "learning_rate": 1.7431448254773943e-05,
+      "loss": 4.0349,
+      "step": 31
+    },
+    {
+      "epoch": 0.11307420494699646,
+      "grad_norm": 4.6858696937561035,
+      "learning_rate": 1.7193398003386514e-05,
+      "loss": 4.0095,
+      "step": 32
+    },
+    {
+      "epoch": 0.1166077738515901,
+      "grad_norm": 3.9068796634674072,
+      "learning_rate": 1.6946583704589973e-05,
+      "loss": 3.6553,
+      "step": 33
+    },
+    {
+      "epoch": 0.12014134275618374,
+      "grad_norm": 4.144792556762695,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 3.6503,
+      "step": 34
+    },
+    {
+      "epoch": 0.12367491166077739,
+      "grad_norm": 3.6011180877685547,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 3.4449,
+      "step": 35
+    },
+    {
+      "epoch": 0.127208480565371,
+      "grad_norm": 4.0844407081604,
+      "learning_rate": 1.6156614753256583e-05,
+      "loss": 3.7941,
+      "step": 36
+    },
+    {
+      "epoch": 0.127208480565371,
+      "eval_loss": 3.6412363052368164,
+      "eval_runtime": 7.1728,
+      "eval_samples_per_second": 33.32,
+      "eval_steps_per_second": 4.182,
+      "step": 36
+    },
+    {
+      "epoch": 0.13074204946996468,
+      "grad_norm": 3.8344345092773438,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 4.0356,
+      "step": 37
+    },
+    {
+      "epoch": 0.13427561837455831,
+      "grad_norm": 4.485532760620117,
+      "learning_rate": 1.5591929034707468e-05,
+      "loss": 3.733,
+      "step": 38
+    },
+    {
+      "epoch": 0.13780918727915195,
+      "grad_norm": 4.423894882202148,
+      "learning_rate": 1.529919264233205e-05,
+      "loss": 3.6177,
+      "step": 39
+    },
+    {
+      "epoch": 0.1413427561837456,
+      "grad_norm": 3.844165325164795,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 3.6761,
+      "step": 40
+    },
+    {
+      "epoch": 0.14487632508833923,
+      "grad_norm": 3.5136537551879883,
+      "learning_rate": 1.469471562785891e-05,
+      "loss": 3.6134,
+      "step": 41
+    },
+    {
+      "epoch": 0.14840989399293286,
+      "grad_norm": 3.5087645053863525,
+      "learning_rate": 1.4383711467890776e-05,
+      "loss": 3.557,
+      "step": 42
+    },
+    {
+      "epoch": 0.1519434628975265,
+      "grad_norm": 3.902492046356201,
+      "learning_rate": 1.4067366430758004e-05,
+      "loss": 3.6009,
+      "step": 43
+    },
+    {
+      "epoch": 0.15547703180212014,
+      "grad_norm": 3.4406399726867676,
+      "learning_rate": 1.3746065934159123e-05,
+      "loss": 3.4341,
+      "step": 44
+    },
+    {
+      "epoch": 0.15901060070671377,
+      "grad_norm": 3.278090715408325,
+      "learning_rate": 1.342020143325669e-05,
+      "loss": 3.1567,
+      "step": 45
+    },
+    {
+      "epoch": 0.15901060070671377,
+      "eval_loss": 3.398796796798706,
+      "eval_runtime": 7.1641,
+      "eval_samples_per_second": 33.361,
+      "eval_steps_per_second": 4.188,
+      "step": 45
+    },
+    {
+      "epoch": 0.1625441696113074,
+      "grad_norm": 3.7867252826690674,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 3.3983,
+      "step": 46
+    },
+    {
+      "epoch": 0.16607773851590105,
+      "grad_norm": 4.200196743011475,
+      "learning_rate": 1.2756373558169992e-05,
+      "loss": 3.6074,
+      "step": 47
+    },
+    {
+      "epoch": 0.1696113074204947,
+      "grad_norm": 3.7975761890411377,
+      "learning_rate": 1.2419218955996677e-05,
+      "loss": 3.6216,
+      "step": 48
+    },
+    {
+      "epoch": 0.17314487632508835,
+      "grad_norm": 3.228562355041504,
+      "learning_rate": 1.2079116908177592e-05,
+      "loss": 3.2195,
+      "step": 49
+    },
+    {
+      "epoch": 0.17667844522968199,
+      "grad_norm": 3.666325092315674,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 3.2573,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2419306423910400.0,
+  "total_flos": 4838612847820800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null