Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9068ab8b12910134390193df6e671ee9804adf662d99ae80242950652f33de89
+oid sha256:689e56aaf984fcdfc4b933e871b56d04cdd4fa8c7abff9a2d9129b074eb6cece
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a14b177ed9c9ec4660cb215498d18d35699f02daac2a5925d98f10b92bc75b5
+oid sha256:32b2b81bc20055e2789ae7a34d48bbd73ee0a8a7126174c9e6451384ec13a650
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fbb9dcf0da2d9b5d3a9949a2085ac919ae660b7274cef9931a3a5782eab72ae
+oid sha256:5bf85c58cca5aae7d759797e66cb053a57988fcfe19dedb65a2573f97c517485
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
+oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008209014128976242,
+  "epoch": 0.012313521193464362,
   "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": 18.112,
       "eval_steps_per_second": 9.056,
       "step": 26
+    },
+    {
+      "epoch": 0.008524745441629173,
+      "grad_norm": 2.8270161151885986,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 4.3127,
+      "step": 27
+    },
+    {
+      "epoch": 0.008840476754282105,
+      "grad_norm": 2.343597173690796,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 4.7903,
+      "step": 28
+    },
+    {
+      "epoch": 0.009156208066935038,
+      "grad_norm": 2.1331675052642822,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 3.7894,
+      "step": 29
+    },
+    {
+      "epoch": 0.00947193937958797,
+      "grad_norm": 2.6220457553863525,
+      "learning_rate": 0.0001,
+      "loss": 4.2415,
+      "step": 30
+    },
+    {
+      "epoch": 0.009787670692240904,
+      "grad_norm": 2.525392532348633,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 4.3988,
+      "step": 31
+    },
+    {
+      "epoch": 0.010103402004893835,
+      "grad_norm": 2.459665298461914,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 4.202,
+      "step": 32
+    },
+    {
+      "epoch": 0.010419133317546767,
+      "grad_norm": 2.508035182952881,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 4.4926,
+      "step": 33
+    },
+    {
+      "epoch": 0.0107348646301997,
+      "grad_norm": 2.238208293914795,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 4.3429,
+      "step": 34
+    },
+    {
+      "epoch": 0.011050595942852633,
+      "grad_norm": 1.8518725633621216,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 3.7004,
+      "step": 35
+    },
+    {
+      "epoch": 0.011366327255505565,
+      "grad_norm": 2.1632683277130127,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 3.6473,
+      "step": 36
+    },
+    {
+      "epoch": 0.011682058568158496,
+      "grad_norm": 2.4588687419891357,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 4.118,
+      "step": 37
+    },
+    {
+      "epoch": 0.011997789880811429,
+      "grad_norm": 1.9152288436889648,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.8266,
+      "step": 38
+    },
+    {
+      "epoch": 0.012313521193464362,
+      "grad_norm": 2.8986527919769287,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 4.5158,
+      "step": 39
+    },
+    {
+      "epoch": 0.012313521193464362,
+      "eval_loss": 0.9916089773178101,
+      "eval_runtime": 73.6951,
+      "eval_samples_per_second": 18.102,
+      "eval_steps_per_second": 9.051,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8311338801561600.0,
+  "total_flos": 1.242743039852544e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null