Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95f291e7fe175f804ddf0a4aed92fb5b81dbb0f102117d81ea235cec993534bf
+oid sha256:565694a02d1a680ad13e6d5c287bf364d75ba1df1968e700df48d5b139619be8
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bef7e90d5a05f32e481e804985478363555360d80a6e9cc8f4cf6d08358516c3
+oid sha256:7d201213f522b4297793e9cae51caef747a5e3fa1fe3af92f0f21681c0637437
 size 42608388

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2cd389488883700d00020d6285217a7094385314dca96ad9c88a040f7b62272
+oid sha256:f8da9606d70da26debcc91dc4a0b0ee52744429e41e4aaa27c50a18cdc492729
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c01f0e9cf526f4fc1579c2da7faf501a14dd022db8358e69b59096f999aab30
+oid sha256:3d3686b687745fcb51a0130846462af73ebb73b22def0cd1248dd8c0cf83e372
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
+oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03526021359552466,
+  "epoch": 0.052890320393287,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 18.584,
       "eval_steps_per_second": 4.646,
       "step": 26
+    },
+    {
+      "epoch": 0.036616375656891,
+      "grad_norm": 0.3312748372554779,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.241,
+      "step": 27
+    },
+    {
+      "epoch": 0.03797253771825733,
+      "grad_norm": 0.3222319781780243,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.2303,
+      "step": 28
+    },
+    {
+      "epoch": 0.039328699779623666,
+      "grad_norm": 0.3243453800678253,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.227,
+      "step": 29
+    },
+    {
+      "epoch": 0.040684861840989996,
+      "grad_norm": 0.32615312933921814,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.2461,
+      "step": 30
+    },
+    {
+      "epoch": 0.04204102390235633,
+      "grad_norm": 0.3400299847126007,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2265,
+      "step": 31
+    },
+    {
+      "epoch": 0.04339718596372266,
+      "grad_norm": 0.33165961503982544,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2531,
+      "step": 32
+    },
+    {
+      "epoch": 0.044753348025089,
+      "grad_norm": 0.30722764134407043,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.2222,
+      "step": 33
+    },
+    {
+      "epoch": 0.04610951008645533,
+      "grad_norm": 0.31792157888412476,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.2555,
+      "step": 34
+    },
+    {
+      "epoch": 0.047465672147821665,
+      "grad_norm": 0.308610737323761,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.2574,
+      "step": 35
+    },
+    {
+      "epoch": 0.048821834209187995,
+      "grad_norm": 0.3103911876678467,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.2055,
+      "step": 36
+    },
+    {
+      "epoch": 0.05017799627055433,
+      "grad_norm": 0.33152303099632263,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.2281,
+      "step": 37
+    },
+    {
+      "epoch": 0.05153415833192066,
+      "grad_norm": 0.3187631368637085,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2171,
+      "step": 38
+    },
+    {
+      "epoch": 0.052890320393287,
+      "grad_norm": 0.3220902681350708,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.2111,
+      "step": 39
+    },
+    {
+      "epoch": 0.052890320393287,
+      "eval_loss": 1.2134052515029907,
+      "eval_runtime": 267.2229,
+      "eval_samples_per_second": 18.591,
+      "eval_steps_per_second": 4.648,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6728164252254208e+17,
+  "total_flos": 2.5092246378381312e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null