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:ba3456719c5c09db30a3cd8c123271dd246f821efdd7ebf2e2fa6e9e78cb2d42
+oid sha256:3cba42492e4359436c8e95f1e537c68b51251cd15e1825b82e7e04ef06ccec71
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc92da3f484ae8c4d0ff5951c400703e52039d5a8a9c2b5363577a1392194520
+oid sha256:b93625a6c71c7ef43cc67bb08fd7b88b6fd434cfe018f0ae8c4cc2563fcd21c0
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424d06375131df3df5d4883391c61f995c66d877e893fd245f2c624058954297
+oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0017186815729241548,
+  "epoch": 0.0025780223593862323,
   "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": 26.162,
       "eval_steps_per_second": 13.081,
       "step": 26
+    },
+    {
+      "epoch": 0.0017847847103443148,
+      "grad_norm": 6.071116924285889,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 18.2956,
+      "step": 27
+    },
+    {
+      "epoch": 0.0018508878477644746,
+      "grad_norm": 7.337187767028809,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 17.3422,
+      "step": 28
+    },
+    {
+      "epoch": 0.0019169909851846343,
+      "grad_norm": 7.344765663146973,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 17.1084,
+      "step": 29
+    },
+    {
+      "epoch": 0.0019830941226047943,
+      "grad_norm": 5.357908248901367,
+      "learning_rate": 5e-05,
+      "loss": 16.2214,
+      "step": 30
+    },
+    {
+      "epoch": 0.002049197260024954,
+      "grad_norm": 5.5231170654296875,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 14.8315,
+      "step": 31
+    },
+    {
+      "epoch": 0.002115300397445114,
+      "grad_norm": 6.47795295715332,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 18.0969,
+      "step": 32
+    },
+    {
+      "epoch": 0.0021814035348652733,
+      "grad_norm": 7.260648250579834,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 15.8214,
+      "step": 33
+    },
+    {
+      "epoch": 0.0022475066722854333,
+      "grad_norm": 7.220073699951172,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 12.7376,
+      "step": 34
+    },
+    {
+      "epoch": 0.0023136098097055933,
+      "grad_norm": 7.377877712249756,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 17.0262,
+      "step": 35
+    },
+    {
+      "epoch": 0.002379712947125753,
+      "grad_norm": 5.653985977172852,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 14.1928,
+      "step": 36
+    },
+    {
+      "epoch": 0.0024458160845459128,
+      "grad_norm": 5.363378047943115,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 15.5034,
+      "step": 37
+    },
+    {
+      "epoch": 0.0025119192219660727,
+      "grad_norm": 5.481878280639648,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 15.7485,
+      "step": 38
+    },
+    {
+      "epoch": 0.0025780223593862323,
+      "grad_norm": 5.979918956756592,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 13.8195,
+      "step": 39
+    },
+    {
+      "epoch": 0.0025780223593862323,
+      "eval_loss": NaN,
+      "eval_runtime": 974.5754,
+      "eval_samples_per_second": 26.144,
+      "eval_steps_per_second": 13.072,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.292873277571072e+16,
+  "total_flos": 4.939309916356608e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null