Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cf1bfd10af0bb7b43c0d7fc8ea6dbfbfaf9222674ebb996bced9bf770e9b221
+oid sha256:15adf756fd8d29ee33087651b79bd8bfbe85dcd317cd3623da4a14da763b855e
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff3d23fc33dafd7c968587776302cc62dbf39181bf0758748ad91588b0067692
+oid sha256:5d722d182e6f0cd3937dca970888df5afb8b4b8576cb0374a50418f7f04176a3
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec321806b1d45557a32bf6b51a82e1fbe0f11344d9834ca94ecdc32cb694ca75
+oid sha256:274bad6912abd00f7939e88b2927c448da73420ebf4efa2b0a54eb2c00324194
 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": 0.0034338300940869445,
+  "epoch": 0.006867660188173889,
   "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": 0.9741,
       "step": 25
+    },
+    {
+      "epoch": 0.003571183297850422,
+      "grad_norm": 1.5280568599700928,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.7625,
+      "step": 26
+    },
+    {
+      "epoch": 0.0037085365016139003,
+      "grad_norm": 2.04048490524292,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.0372,
+      "step": 27
+    },
+    {
+      "epoch": 0.0037085365016139003,
+      "eval_loss": 1.0555644035339355,
+      "eval_runtime": 1498.6144,
+      "eval_samples_per_second": 4.091,
+      "eval_steps_per_second": 0.512,
+      "step": 27
+    },
+    {
+      "epoch": 0.003845889705377378,
+      "grad_norm": 2.096092462539673,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.0439,
+      "step": 28
+    },
+    {
+      "epoch": 0.003983242909140856,
+      "grad_norm": 4.1492486000061035,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.1595,
+      "step": 29
+    },
+    {
+      "epoch": 0.004120596112904333,
+      "grad_norm": 2.5651235580444336,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.0073,
+      "step": 30
+    },
+    {
+      "epoch": 0.004257949316667811,
+      "grad_norm": 2.9436209201812744,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.7517,
+      "step": 31
+    },
+    {
+      "epoch": 0.0043953025204312894,
+      "grad_norm": 2.7678189277648926,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.8658,
+      "step": 32
+    },
+    {
+      "epoch": 0.004532655724194767,
+      "grad_norm": 2.158916711807251,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.9779,
+      "step": 33
+    },
+    {
+      "epoch": 0.004670008927958245,
+      "grad_norm": 1.9354743957519531,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.619,
+      "step": 34
+    },
+    {
+      "epoch": 0.004807362131721722,
+      "grad_norm": 2.492863893508911,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.709,
+      "step": 35
+    },
+    {
+      "epoch": 0.0049447153354852,
+      "grad_norm": 1.5627326965332031,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.5263,
+      "step": 36
+    },
+    {
+      "epoch": 0.0049447153354852,
+      "eval_loss": 0.6903370022773743,
+      "eval_runtime": 1497.3825,
+      "eval_samples_per_second": 4.094,
+      "eval_steps_per_second": 0.512,
+      "step": 36
+    },
+    {
+      "epoch": 0.005082068539248678,
+      "grad_norm": 2.2282795906066895,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.4985,
+      "step": 37
+    },
+    {
+      "epoch": 0.005219421743012155,
+      "grad_norm": 4.293792247772217,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.7172,
+      "step": 38
+    },
+    {
+      "epoch": 0.0053567749467756335,
+      "grad_norm": 3.52012038230896,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.5202,
+      "step": 39
+    },
+    {
+      "epoch": 0.005494128150539112,
+      "grad_norm": 2.2252063751220703,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.4629,
+      "step": 40
+    },
+    {
+      "epoch": 0.005631481354302589,
+      "grad_norm": 4.003269195556641,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.7875,
+      "step": 41
+    },
+    {
+      "epoch": 0.005768834558066067,
+      "grad_norm": 3.8624725341796875,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.7379,
+      "step": 42
+    },
+    {
+      "epoch": 0.005906187761829545,
+      "grad_norm": 4.79985237121582,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.5905,
+      "step": 43
+    },
+    {
+      "epoch": 0.006043540965593022,
+      "grad_norm": 2.62689471244812,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.3897,
+      "step": 44
+    },
+    {
+      "epoch": 0.0061808941693565,
+      "grad_norm": 2.633169412612915,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.4792,
+      "step": 45
+    },
+    {
+      "epoch": 0.0061808941693565,
+      "eval_loss": 0.4047314524650574,
+      "eval_runtime": 1497.4649,
+      "eval_samples_per_second": 4.094,
+      "eval_steps_per_second": 0.512,
+      "step": 45
+    },
+    {
+      "epoch": 0.006318247373119978,
+      "grad_norm": 2.664032459259033,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.4602,
+      "step": 46
+    },
+    {
+      "epoch": 0.006455600576883456,
+      "grad_norm": 2.5823395252227783,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.6398,
+      "step": 47
+    },
+    {
+      "epoch": 0.006592953780646934,
+      "grad_norm": 2.515225648880005,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.3104,
+      "step": 48
+    },
+    {
+      "epoch": 0.006730306984410411,
+      "grad_norm": 2.0998854637145996,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.3107,
+      "step": 49
+    },
+    {
+      "epoch": 0.006867660188173889,
+      "grad_norm": 2.1281323432922363,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.2989,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.415857563500544e+16,
+  "total_flos": 2.617690146471936e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null