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:ecb3ed0b3912352c632bcf8d19b5b514f406297509315ee3aab3ed8adda3ae5a
+oid sha256:a36b71b9f5eba262d22c1e3205584a4af5b92b37cd0f1f2e3ee49247c8c1bdc1
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f157b504b01bc0ce8115922df7a0c7dd2068325060d6cf59548673d3c5565807
+oid sha256:8c737a14d742da4bca36c82cc97b56e222100702f7696c05e097ef78de33b433
 size 332574358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06decf0cb685431e370148d342f27ea5d06429098903509741d0b8e63829aa44
+oid sha256:087a2ae65a4a30ca6315e22599816ba4b93588344c447989bc4f3501c2bf67eb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3f6891a2dad4098258cacbb534eda6cb23344f32c27a937c7da2508a5fd6662
+oid sha256:ef593f391c66ba3ea6e8dea3b2aa8e19ae1f574e3c6a18c96ee14293016120aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.022768670309653915,
+  "epoch": 0.04553734061930783,
   "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": 12.265,
       "eval_steps_per_second": 6.146,
       "step": 25
+    },
+    {
+      "epoch": 0.023679417122040074,
+      "grad_norm": 3.8335983753204346,
+      "learning_rate": 3.84324902086706e-05,
+      "loss": 1.6246,
+      "step": 26
+    },
+    {
+      "epoch": 0.02459016393442623,
+      "grad_norm": 4.2963151931762695,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.8721,
+      "step": 27
+    },
+    {
+      "epoch": 0.025500910746812388,
+      "grad_norm": 4.064708709716797,
+      "learning_rate": 3.654371533087586e-05,
+      "loss": 1.6337,
+      "step": 28
+    },
+    {
+      "epoch": 0.026411657559198543,
+      "grad_norm": 3.6003475189208984,
+      "learning_rate": 3.556545654351749e-05,
+      "loss": 1.1948,
+      "step": 29
+    },
+    {
+      "epoch": 0.0273224043715847,
+      "grad_norm": 4.95332145690918,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 1.7435,
+      "step": 30
+    },
+    {
+      "epoch": 0.028233151183970857,
+      "grad_norm": 5.380415439605713,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 1.3499,
+      "step": 31
+    },
+    {
+      "epoch": 0.029143897996357013,
+      "grad_norm": 4.800806522369385,
+      "learning_rate": 3.251764498760683e-05,
+      "loss": 1.5518,
+      "step": 32
+    },
+    {
+      "epoch": 0.030054644808743168,
+      "grad_norm": 4.674807071685791,
+      "learning_rate": 3.147047612756302e-05,
+      "loss": 1.5142,
+      "step": 33
+    },
+    {
+      "epoch": 0.030965391621129327,
+      "grad_norm": 4.52117919921875,
+      "learning_rate": 3.0410990348452573e-05,
+      "loss": 1.4617,
+      "step": 34
+    },
+    {
+      "epoch": 0.031876138433515486,
+      "grad_norm": 5.159020900726318,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 1.3345,
+      "step": 35
+    },
+    {
+      "epoch": 0.03278688524590164,
+      "grad_norm": 5.662403583526611,
+      "learning_rate": 2.8263154805501297e-05,
+      "loss": 1.4164,
+      "step": 36
+    },
+    {
+      "epoch": 0.033697632058287796,
+      "grad_norm": 5.426482677459717,
+      "learning_rate": 2.717889356869146e-05,
+      "loss": 1.2144,
+      "step": 37
+    },
+    {
+      "epoch": 0.03460837887067395,
+      "grad_norm": 5.797895908355713,
+      "learning_rate": 2.6090484684133404e-05,
+      "loss": 1.3768,
+      "step": 38
+    },
+    {
+      "epoch": 0.03551912568306011,
+      "grad_norm": 6.419762134552002,
+      "learning_rate": 2.5e-05,
+      "loss": 1.4736,
+      "step": 39
+    },
+    {
+      "epoch": 0.03642987249544627,
+      "grad_norm": 5.924313545227051,
+      "learning_rate": 2.3909515315866605e-05,
+      "loss": 1.2825,
+      "step": 40
+    },
+    {
+      "epoch": 0.037340619307832425,
+      "grad_norm": 6.173450469970703,
+      "learning_rate": 2.2821106431308544e-05,
+      "loss": 1.3105,
+      "step": 41
+    },
+    {
+      "epoch": 0.03825136612021858,
+      "grad_norm": 8.242639541625977,
+      "learning_rate": 2.173684519449872e-05,
+      "loss": 1.3073,
+      "step": 42
+    },
+    {
+      "epoch": 0.039162112932604735,
+      "grad_norm": 8.869377136230469,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 1.4705,
+      "step": 43
+    },
+    {
+      "epoch": 0.04007285974499089,
+      "grad_norm": 8.427241325378418,
+      "learning_rate": 1.958900965154743e-05,
+      "loss": 1.6696,
+      "step": 44
+    },
+    {
+      "epoch": 0.040983606557377046,
+      "grad_norm": 9.052663803100586,
+      "learning_rate": 1.852952387243698e-05,
+      "loss": 1.2254,
+      "step": 45
+    },
+    {
+      "epoch": 0.04189435336976321,
+      "grad_norm": 7.14196252822876,
+      "learning_rate": 1.7482355012393177e-05,
+      "loss": 1.314,
+      "step": 46
+    },
+    {
+      "epoch": 0.042805100182149364,
+      "grad_norm": 10.285764694213867,
+      "learning_rate": 1.6449496416858284e-05,
+      "loss": 1.9592,
+      "step": 47
+    },
+    {
+      "epoch": 0.04371584699453552,
+      "grad_norm": 11.626080513000488,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 1.7412,
+      "step": 48
+    },
+    {
+      "epoch": 0.044626593806921674,
+      "grad_norm": 16.58131217956543,
+      "learning_rate": 1.443454345648252e-05,
+      "loss": 2.785,
+      "step": 49
+    },
+    {
+      "epoch": 0.04553734061930783,
+      "grad_norm": 47.45877456665039,
+      "learning_rate": 1.3456284669124158e-05,
+      "loss": 4.9434,
+      "step": 50
+    },
+    {
+      "epoch": 0.04553734061930783,
+      "eval_loss": 1.322178840637207,
+      "eval_runtime": 37.7906,
+      "eval_samples_per_second": 12.252,
+      "eval_steps_per_second": 6.139,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5331404130877440.0,
+  "total_flos": 1.040893187457024e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null