Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46f48bd5216b098cfe2c17604e60900c2875caf68690f87a02c2e5e3e745dd56
+oid sha256:3b3a6143cf407cb072ab9cac3ba89eb179ab64b176e84dd1c0661aadd1ff0d6a
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99cd1f0da7ae31cb8cfb3d96cb082d28bd4e3bb6366c0022f7371c67c630ddc1
+oid sha256:67e22455ba59dfbab988be608fd904788817a8d8acc140ceb1a045125d5e4523
 size 127788180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4d8d8ebcb46d94260f53b4b9a201e9e40c1f599536d1ebd047721586dc3451b
+oid sha256:a81724f6b9c5247f3a62cf570fa01adcf6cc8b5fd453850cfb8aab6bd795e61c
 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": 0.0925884709548186,
+  "epoch": 0.13888270643222791,
   "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": 4.265,
       "eval_steps_per_second": 2.137,
       "step": 26
+    },
+    {
+      "epoch": 0.0961495659915424,
+      "grad_norm": 1.4864414930343628,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 2.1355,
+      "step": 27
+    },
+    {
+      "epoch": 0.09971066102826619,
+      "grad_norm": 1.316426396369934,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 1.9895,
+      "step": 28
+    },
+    {
+      "epoch": 0.10327175606498998,
+      "grad_norm": 1.437731146812439,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 2.0277,
+      "step": 29
+    },
+    {
+      "epoch": 0.10683285110171378,
+      "grad_norm": 1.660027027130127,
+      "learning_rate": 5e-05,
+      "loss": 2.228,
+      "step": 30
+    },
+    {
+      "epoch": 0.11039394613843757,
+      "grad_norm": 1.3694123029708862,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 1.9222,
+      "step": 31
+    },
+    {
+      "epoch": 0.11395504117516136,
+      "grad_norm": 1.639948844909668,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.158,
+      "step": 32
+    },
+    {
+      "epoch": 0.11751613621188516,
+      "grad_norm": 2.648879051208496,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 2.0388,
+      "step": 33
+    },
+    {
+      "epoch": 0.12107723124860895,
+      "grad_norm": 1.5599783658981323,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.4029,
+      "step": 34
+    },
+    {
+      "epoch": 0.12463832628533274,
+      "grad_norm": 1.3389352560043335,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.7365,
+      "step": 35
+    },
+    {
+      "epoch": 0.12819942132205653,
+      "grad_norm": 1.6567745208740234,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 2.1814,
+      "step": 36
+    },
+    {
+      "epoch": 0.13176051635878033,
+      "grad_norm": 1.775384783744812,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 2.3459,
+      "step": 37
+    },
+    {
+      "epoch": 0.1353216113955041,
+      "grad_norm": 1.3190244436264038,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.7901,
+      "step": 38
+    },
+    {
+      "epoch": 0.13888270643222791,
+      "grad_norm": 1.489214539527893,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 1.8801,
+      "step": 39
+    },
+    {
+      "epoch": 0.13888270643222791,
+      "eval_loss": 2.036982297897339,
+      "eval_runtime": 110.9189,
+      "eval_samples_per_second": 4.264,
+      "eval_steps_per_second": 2.137,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.6465766450659328e+17,
+  "total_flos": 3.969864967598899e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null