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:a2ef4f70a17f12a86f5b4ce5f36c4d56c1c3d3b13dd55946ed669b7d84707f34
+oid sha256:bbc5d99ccaee865283f5e6c63796fd6a71df7815bd9922ecaaa62053bc9773c5
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:218b555b3e59b81ed9623c86c1c3b81cb7b7c01b4a6973dd228fe84b22b1d7c7
+oid sha256:724759950a3b8cebdb7ffd60cb89ac9b6d7227a8e476faee5a0c4b8e6ba05b29
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c334162029911df951f21e152e5ddf37f5d979575a6d060ad1d369247ccd5d4
+oid sha256:c08c9f2db3519491f65c896dc5570f0688363fea4110372251c117212111fc45
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007387488549392749,
+  "epoch": 0.0014774977098785497,
   "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": 9.330127018922194e-05,
       "loss": 2.4414,
       "step": 25
+    },
+    {
+      "epoch": 0.0007682988091368458,
+      "grad_norm": 2.872539520263672,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 2.0839,
+      "step": 26
+    },
+    {
+      "epoch": 0.0007978487633344168,
+      "grad_norm": 3.146365165710449,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 2.1332,
+      "step": 27
+    },
+    {
+      "epoch": 0.0007978487633344168,
+      "eval_loss": 1.0715131759643555,
+      "eval_runtime": 5871.8151,
+      "eval_samples_per_second": 4.853,
+      "eval_steps_per_second": 0.607,
+      "step": 27
+    },
+    {
+      "epoch": 0.0008273987175319878,
+      "grad_norm": 5.3669538497924805,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.253,
+      "step": 28
+    },
+    {
+      "epoch": 0.0008569486717295589,
+      "grad_norm": 2.2301602363586426,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.9265,
+      "step": 29
+    },
+    {
+      "epoch": 0.0008864986259271298,
+      "grad_norm": 3.5137948989868164,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 2.5722,
+      "step": 30
+    },
+    {
+      "epoch": 0.0009160485801247008,
+      "grad_norm": 2.713407516479492,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 2.2216,
+      "step": 31
+    },
+    {
+      "epoch": 0.0009455985343222718,
+      "grad_norm": 2.0557379722595215,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.8588,
+      "step": 32
+    },
+    {
+      "epoch": 0.0009751484885198428,
+      "grad_norm": 2.0198111534118652,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.8648,
+      "step": 33
+    },
+    {
+      "epoch": 0.0010046984427174138,
+      "grad_norm": 2.3632073402404785,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 2.1044,
+      "step": 34
+    },
+    {
+      "epoch": 0.0010342483969149848,
+      "grad_norm": 1.9320204257965088,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.8379,
+      "step": 35
+    },
+    {
+      "epoch": 0.0010637983511125558,
+      "grad_norm": 1.7286494970321655,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.3026,
+      "step": 36
+    },
+    {
+      "epoch": 0.0010637983511125558,
+      "eval_loss": 0.9508614540100098,
+      "eval_runtime": 5872.34,
+      "eval_samples_per_second": 4.853,
+      "eval_steps_per_second": 0.607,
+      "step": 36
+    },
+    {
+      "epoch": 0.0010933483053101269,
+      "grad_norm": 1.882214069366455,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.5322,
+      "step": 37
+    },
+    {
+      "epoch": 0.0011228982595076977,
+      "grad_norm": 1.8262519836425781,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.5499,
+      "step": 38
+    },
+    {
+      "epoch": 0.0011524482137052687,
+      "grad_norm": 2.2393839359283447,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.9446,
+      "step": 39
+    },
+    {
+      "epoch": 0.0011819981679028397,
+      "grad_norm": 1.8406883478164673,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.3716,
+      "step": 40
+    },
+    {
+      "epoch": 0.0012115481221004107,
+      "grad_norm": 2.10400128364563,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 2.1462,
+      "step": 41
+    },
+    {
+      "epoch": 0.0012410980762979818,
+      "grad_norm": 2.732954978942871,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.8046,
+      "step": 42
+    },
+    {
+      "epoch": 0.0012706480304955528,
+      "grad_norm": 2.190100908279419,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.6991,
+      "step": 43
+    },
+    {
+      "epoch": 0.0013001979846931238,
+      "grad_norm": 2.131598472595215,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.7265,
+      "step": 44
+    },
+    {
+      "epoch": 0.0013297479388906946,
+      "grad_norm": 2.4191086292266846,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.0866,
+      "step": 45
+    },
+    {
+      "epoch": 0.0013297479388906946,
+      "eval_loss": 0.9063876867294312,
+      "eval_runtime": 5872.647,
+      "eval_samples_per_second": 4.853,
+      "eval_steps_per_second": 0.607,
+      "step": 45
+    },
+    {
+      "epoch": 0.0013592978930882656,
+      "grad_norm": 2.1638476848602295,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.636,
+      "step": 46
+    },
+    {
+      "epoch": 0.0013888478472858367,
+      "grad_norm": 3.2080116271972656,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 2.1953,
+      "step": 47
+    },
+    {
+      "epoch": 0.0014183978014834077,
+      "grad_norm": 2.4850316047668457,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 2.1594,
+      "step": 48
+    },
+    {
+      "epoch": 0.0014479477556809787,
+      "grad_norm": 2.722036123275757,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 2.6908,
+      "step": 49
+    },
+    {
+      "epoch": 0.0014774977098785497,
+      "grad_norm": 2.7537569999694824,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 2.0251,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1739149811712e+16,
+  "total_flos": 6.3478299623424e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null