Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3be8adad683e14181523c84c06648d17193c9042de9e2a38676127a439c6d4f
+oid sha256:425aec1a8f509aa949db8802e231628752bd4eba220344fab0231408442d53b5
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ddb576e6d56d5e80e05c28f7e8eb5d3e742bcf6f5d13d2cf3013478c6d7bd3d
+oid sha256:6d19b98b304713107bf9afdee89253c04617faef5e1c35f25b5b055c7d4de8de
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89becb00dfe197da4b326b0e6b72683a9138572945875800aafb42add5203181
+oid sha256:2974389e592a195c17496cc71e3751033043ca9abc087913ab145b52e73b99b5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d914dc409ae93ac75985631a9974025ebaa397f621307eef226e7d6e1076a1f6
+oid sha256:babd43118aa66a4f5266d730539cf7f09611158b169d9e63dbcb83f6bbaa8626
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004417985619456809,
+  "epoch": 0.006626978429185213,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 2.902,
       "eval_steps_per_second": 1.451,
       "step": 50
+    },
+    {
+      "epoch": 0.004506345331845945,
+      "grad_norm": 7.406082630157471,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 7.7452,
+      "step": 51
+    },
+    {
+      "epoch": 0.004594705044235081,
+      "grad_norm": 10.304743766784668,
+      "learning_rate": 4.6270039165317605e-05,
+      "loss": 8.5386,
+      "step": 52
+    },
+    {
+      "epoch": 0.004683064756624217,
+      "grad_norm": 8.669404983520508,
+      "learning_rate": 4.264235636489542e-05,
+      "loss": 7.5627,
+      "step": 53
+    },
+    {
+      "epoch": 0.004771424469013353,
+      "grad_norm": 11.453923225402832,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 11.6111,
+      "step": 54
+    },
+    {
+      "epoch": 0.004859784181402489,
+      "grad_norm": 9.022344589233398,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 7.1967,
+      "step": 55
+    },
+    {
+      "epoch": 0.004948143893791626,
+      "grad_norm": 8.07685375213623,
+      "learning_rate": 3.244097923843398e-05,
+      "loss": 6.9913,
+      "step": 56
+    },
+    {
+      "epoch": 0.005036503606180762,
+      "grad_norm": 18.292648315429688,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 7.267,
+      "step": 57
+    },
+    {
+      "epoch": 0.005124863318569898,
+      "grad_norm": 6.400746822357178,
+      "learning_rate": 2.6272266318987603e-05,
+      "loss": 5.9861,
+      "step": 58
+    },
+    {
+      "epoch": 0.005213223030959034,
+      "grad_norm": 6.002554893493652,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 5.5134,
+      "step": 59
+    },
+    {
+      "epoch": 0.00530158274334817,
+      "grad_norm": 8.174169540405273,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 6.7454,
+      "step": 60
+    },
+    {
+      "epoch": 0.005389942455737306,
+      "grad_norm": 9.708706855773926,
+      "learning_rate": 1.808479557110081e-05,
+      "loss": 7.318,
+      "step": 61
+    },
+    {
+      "epoch": 0.0054783021681264425,
+      "grad_norm": 7.366970062255859,
+      "learning_rate": 1.566085541871145e-05,
+      "loss": 7.1856,
+      "step": 62
+    },
+    {
+      "epoch": 0.0055666618805155785,
+      "grad_norm": 8.115883827209473,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 6.7277,
+      "step": 63
+    },
+    {
+      "epoch": 0.0056550215929047154,
+      "grad_norm": 7.192087173461914,
+      "learning_rate": 1.129891668217783e-05,
+      "loss": 5.8814,
+      "step": 64
+    },
+    {
+      "epoch": 0.0057433813052938515,
+      "grad_norm": 10.194598197937012,
+      "learning_rate": 9.369221296335006e-06,
+      "loss": 7.0609,
+      "step": 65
+    },
+    {
+      "epoch": 0.0058317410176829875,
+      "grad_norm": 8.331764221191406,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 6.5664,
+      "step": 66
+    },
+    {
+      "epoch": 0.005920100730072124,
+      "grad_norm": 9.948031425476074,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 7.0316,
+      "step": 67
+    },
+    {
+      "epoch": 0.00600846044246126,
+      "grad_norm": 7.982971668243408,
+      "learning_rate": 4.628304925177318e-06,
+      "loss": 7.4487,
+      "step": 68
+    },
+    {
+      "epoch": 0.006096820154850396,
+      "grad_norm": 16.90338897705078,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 11.6838,
+      "step": 69
+    },
+    {
+      "epoch": 0.006185179867239532,
+      "grad_norm": 6.867629528045654,
+      "learning_rate": 2.3703992880066638e-06,
+      "loss": 7.1539,
+      "step": 70
+    },
+    {
+      "epoch": 0.006273539579628669,
+      "grad_norm": 7.886899471282959,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 6.606,
+      "step": 71
+    },
+    {
+      "epoch": 0.006361899292017805,
+      "grad_norm": 7.660629749298096,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 9.0877,
+      "step": 72
+    },
+    {
+      "epoch": 0.006450259004406941,
+      "grad_norm": 11.299578666687012,
+      "learning_rate": 3.805301908254455e-07,
+      "loss": 8.0606,
+      "step": 73
+    },
+    {
+      "epoch": 0.006538618716796077,
+      "grad_norm": 7.190691947937012,
+      "learning_rate": 9.517784181422019e-08,
+      "loss": 8.8902,
+      "step": 74
+    },
+    {
+      "epoch": 0.006626978429185213,
+      "grad_norm": 7.750818729400635,
+      "learning_rate": 0.0,
+      "loss": 6.2261,
+      "step": 75
+    },
+    {
+      "epoch": 0.006626978429185213,
+      "eval_loss": 0.9349557757377625,
+      "eval_runtime": 3279.205,
+      "eval_samples_per_second": 2.906,
+      "eval_steps_per_second": 1.453,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.2695579394048e+17,
+  "total_flos": 1.9043369091072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null