Training in progress, step 76, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b838e37c6acc3226cb23a05e8da8e401052de7ec8d63320c4dea86d5b9791f8
+oid sha256:376fe44127e1c619ce7f8f48e03b3be70c6112912963efdb83b45b7157116c70
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44ab86fafce39c2b8346177e57d4e4368a643eb8bc217de77945ce8f27c78395
+oid sha256:4bcd67acebb815dafe6c18e5d183a0c4822a4089bbe094b44777eed010429c78
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f489b33e4ce6b4592438133f0f8030528235eaffcbc7196d436c439dd611d61
+oid sha256:7abb5da1a5f6ed0ff2bc01b41aa9d26ec6e6330291297067e0c80e58907c54d6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be205ee2b4780d487b513e30ac9c545724d6f8bbbacf91c0e0793417bf18e789
+oid sha256:ff804e87c79ef1262057e5db83d54644262c8d880a0b60fd300d8713fc4bac67
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7574750830564784,
+  "epoch": 1.0099667774086378,
   "eval_steps": 19,
-  "global_step": 57,
+  "global_step": 76,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -438,6 +438,147 @@
       "eval_samples_per_second": 33.96,
       "eval_steps_per_second": 16.98,
       "step": 57
+    },
+    {
+      "epoch": 0.770764119601329,
+      "grad_norm": 0.47311338782310486,
+      "learning_rate": 3.45139266054715e-05,
+      "loss": 0.6306,
+      "step": 58
+    },
+    {
+      "epoch": 0.7840531561461794,
+      "grad_norm": 0.5218926668167114,
+      "learning_rate": 3.099209885178882e-05,
+      "loss": 0.6573,
+      "step": 59
+    },
+    {
+      "epoch": 0.7973421926910299,
+      "grad_norm": 0.48611611127853394,
+      "learning_rate": 2.7626596189492983e-05,
+      "loss": 0.6417,
+      "step": 60
+    },
+    {
+      "epoch": 0.8106312292358804,
+      "grad_norm": 0.48212239146232605,
+      "learning_rate": 2.4425042564574184e-05,
+      "loss": 0.5932,
+      "step": 61
+    },
+    {
+      "epoch": 0.8239202657807309,
+      "grad_norm": 0.4338783919811249,
+      "learning_rate": 2.139469052572127e-05,
+      "loss": 0.3378,
+      "step": 62
+    },
+    {
+      "epoch": 0.8372093023255814,
+      "grad_norm": 0.4200206995010376,
+      "learning_rate": 1.854240479496643e-05,
+      "loss": 0.5499,
+      "step": 63
+    },
+    {
+      "epoch": 0.8504983388704319,
+      "grad_norm": 0.5050457715988159,
+      "learning_rate": 1.587464671688187e-05,
+      "loss": 0.4441,
+      "step": 64
+    },
+    {
+      "epoch": 0.8637873754152824,
+      "grad_norm": 0.552359938621521,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.667,
+      "step": 65
+    },
+    {
+      "epoch": 0.8770764119601329,
+      "grad_norm": 0.4609893262386322,
+      "learning_rate": 1.1116455134507664e-05,
+      "loss": 0.6238,
+      "step": 66
+    },
+    {
+      "epoch": 0.8903654485049833,
+      "grad_norm": 0.5870749950408936,
+      "learning_rate": 9.036800464548157e-06,
+      "loss": 0.7167,
+      "step": 67
+    },
+    {
+      "epoch": 0.9036544850498339,
+      "grad_norm": 0.42279618978500366,
+      "learning_rate": 7.163206698392744e-06,
+      "loss": 0.4892,
+      "step": 68
+    },
+    {
+      "epoch": 0.9169435215946844,
+      "grad_norm": 0.6572357416152954,
+      "learning_rate": 5.499918128533155e-06,
+      "loss": 0.6284,
+      "step": 69
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 0.46049225330352783,
+      "learning_rate": 4.050702638550275e-06,
+      "loss": 0.4833,
+      "step": 70
+    },
+    {
+      "epoch": 0.9435215946843853,
+      "grad_norm": 0.4801192283630371,
+      "learning_rate": 2.818843167645835e-06,
+      "loss": 0.7583,
+      "step": 71
+    },
+    {
+      "epoch": 0.9568106312292359,
+      "grad_norm": 0.518804132938385,
+      "learning_rate": 1.8071302737293295e-06,
+      "loss": 0.7252,
+      "step": 72
+    },
+    {
+      "epoch": 0.9700996677740864,
+      "grad_norm": 0.4595305919647217,
+      "learning_rate": 1.0178558119067315e-06,
+      "loss": 0.5154,
+      "step": 73
+    },
+    {
+      "epoch": 0.9833887043189369,
+      "grad_norm": 0.49823713302612305,
+      "learning_rate": 4.5280774269154115e-07,
+      "loss": 0.6968,
+      "step": 74
+    },
+    {
+      "epoch": 0.9966777408637874,
+      "grad_norm": 0.485995888710022,
+      "learning_rate": 1.1326608169920372e-07,
+      "loss": 0.6319,
+      "step": 75
+    },
+    {
+      "epoch": 1.0099667774086378,
+      "grad_norm": 1.4272960424423218,
+      "learning_rate": 0.0,
+      "loss": 1.1565,
+      "step": 76
+    },
+    {
+      "epoch": 1.0099667774086378,
+      "eval_loss": 0.6746536493301392,
+      "eval_runtime": 0.9405,
+      "eval_samples_per_second": 34.026,
+      "eval_steps_per_second": 17.013,
+      "step": 76
     }
   ],
   "logging_steps": 1,
@@ -452,12 +593,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4715279823667200.0,
+  "total_flos": 6273372287139840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null