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:cff5d8a0dc03431df1dd7b112b5040561cd77ecb9c4a054e00c61bd7289aa5e7
+oid sha256:7e66008611d0628244b8ab9d4d39ea29fddc4d14ad66e856a622a8b67dbe2c67
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f211f901bb966e1acd9f1396d55aeaa4f0fed18b2c6dba683aee75eb182cd13d
+oid sha256:5d822dba7c1a4127b5bcb9a3db27c7410ad74c72c16dfbd20d3ec2b7342e5b6b
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63cb2c1d61d3c0f3f148fb5aac3becfaaf586b2c80fb91d1e0031a8c35a9545f
+oid sha256:d0e4cab0424f552a54d41c88469cda3340d942b36a3070c301d13c7d604c12ca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008274036074797287,
+  "epoch": 0.016548072149594573,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,221 @@
       "eval_samples_per_second": 4.945,
       "eval_steps_per_second": 2.474,
       "step": 25
+    },
+    {
+      "epoch": 0.008604997517789177,
+      "grad_norm": 1.674811601638794,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 3.4598,
+      "step": 26
+    },
+    {
+      "epoch": 0.008935958960781068,
+      "grad_norm": 2.091567039489746,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 3.7612,
+      "step": 27
+    },
+    {
+      "epoch": 0.009266920403772961,
+      "grad_norm": 2.1018764972686768,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 3.6964,
+      "step": 28
+    },
+    {
+      "epoch": 0.009597881846764852,
+      "grad_norm": 1.832294225692749,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 3.6292,
+      "step": 29
+    },
+    {
+      "epoch": 0.009928843289756743,
+      "grad_norm": 2.0582776069641113,
+      "learning_rate": 5e-05,
+      "loss": 2.8792,
+      "step": 30
+    },
+    {
+      "epoch": 0.009928843289756743,
+      "eval_loss": 0.811681866645813,
+      "eval_runtime": 257.1914,
+      "eval_samples_per_second": 4.95,
+      "eval_steps_per_second": 2.477,
+      "step": 30
+    },
+    {
+      "epoch": 0.010259804732748635,
+      "grad_norm": 1.9213557243347168,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 3.4662,
+      "step": 31
+    },
+    {
+      "epoch": 0.010590766175740526,
+      "grad_norm": 2.288318395614624,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 3.3137,
+      "step": 32
+    },
+    {
+      "epoch": 0.010921727618732417,
+      "grad_norm": 1.9459996223449707,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 3.4205,
+      "step": 33
+    },
+    {
+      "epoch": 0.01125268906172431,
+      "grad_norm": 1.8996334075927734,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.5199,
+      "step": 34
+    },
+    {
+      "epoch": 0.0115836505047162,
+      "grad_norm": 2.4128260612487793,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.3873,
+      "step": 35
+    },
+    {
+      "epoch": 0.0115836505047162,
+      "eval_loss": 0.7911669611930847,
+      "eval_runtime": 256.9175,
+      "eval_samples_per_second": 4.955,
+      "eval_steps_per_second": 2.479,
+      "step": 35
+    },
+    {
+      "epoch": 0.011914611947708093,
+      "grad_norm": 2.779157876968384,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 3.2642,
+      "step": 36
+    },
+    {
+      "epoch": 0.012245573390699984,
+      "grad_norm": 2.04453444480896,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 3.3588,
+      "step": 37
+    },
+    {
+      "epoch": 0.012576534833691875,
+      "grad_norm": 1.9138102531433105,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 3.1433,
+      "step": 38
+    },
+    {
+      "epoch": 0.012907496276683767,
+      "grad_norm": 2.5308830738067627,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 3.2754,
+      "step": 39
+    },
+    {
+      "epoch": 0.013238457719675658,
+      "grad_norm": 2.0766677856445312,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.1162,
+      "step": 40
+    },
+    {
+      "epoch": 0.013238457719675658,
+      "eval_loss": 0.7798255085945129,
+      "eval_runtime": 257.4302,
+      "eval_samples_per_second": 4.945,
+      "eval_steps_per_second": 2.474,
+      "step": 40
+    },
+    {
+      "epoch": 0.013569419162667549,
+      "grad_norm": 2.0006625652313232,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 3.2087,
+      "step": 41
+    },
+    {
+      "epoch": 0.013900380605659441,
+      "grad_norm": 2.1602704524993896,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.177,
+      "step": 42
+    },
+    {
+      "epoch": 0.014231342048651332,
+      "grad_norm": 1.935172438621521,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 2.6165,
+      "step": 43
+    },
+    {
+      "epoch": 0.014562303491643223,
+      "grad_norm": 1.9336456060409546,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.9167,
+      "step": 44
+    },
+    {
+      "epoch": 0.014893264934635116,
+      "grad_norm": 1.7702152729034424,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.3973,
+      "step": 45
+    },
+    {
+      "epoch": 0.014893264934635116,
+      "eval_loss": 0.7749022245407104,
+      "eval_runtime": 257.2066,
+      "eval_samples_per_second": 4.949,
+      "eval_steps_per_second": 2.477,
+      "step": 45
+    },
+    {
+      "epoch": 0.015224226377627006,
+      "grad_norm": 1.742775559425354,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 3.1991,
+      "step": 46
+    },
+    {
+      "epoch": 0.015555187820618897,
+      "grad_norm": 2.1770782470703125,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 2.8691,
+      "step": 47
+    },
+    {
+      "epoch": 0.015886149263610788,
+      "grad_norm": 2.1110646724700928,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 2.4055,
+      "step": 48
+    },
+    {
+      "epoch": 0.016217110706602682,
+      "grad_norm": 1.619126796722412,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 3.075,
+      "step": 49
+    },
+    {
+      "epoch": 0.016548072149594573,
+      "grad_norm": 2.098407030105591,
+      "learning_rate": 0.0,
+      "loss": 2.9933,
+      "step": 50
+    },
+    {
+      "epoch": 0.016548072149594573,
+      "eval_loss": 0.7738050818443298,
+      "eval_runtime": 256.8475,
+      "eval_samples_per_second": 4.956,
+      "eval_steps_per_second": 2.48,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -244,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.64348634857472e+16,
+  "total_flos": 3.28697269714944e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null