Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9954a1685a6e981d2cbcb7fef450b316454356d9bfc228ca35b8663590f631fa
+oid sha256:ad1c3e59efeb6821d98b4d4a1a0b8ed86b7ff9dc029bc7f604f74231fd8a4d71
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c48d0d6028a95807aaf6e350329fcc46fe1e2797b38ebec016d7bc6bae1641dc
+oid sha256:882cc645acd3c79d89c51d611acbc1dcf17d40023f742d5d777085fce613f05b
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06433e1beb51c034458d1b227ee25690394f4c8d72f8fe8edad932bedf1cad65
+oid sha256:43de271a9dc1872b08a0792489357aea0ba92fca6b88a248cee696bc715840fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4429678848283499,
+  "epoch": 0.6644518272425249,
   "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": 2.876,
       "eval_steps_per_second": 1.453,
       "step": 50
+    },
+    {
+      "epoch": 0.45182724252491696,
+      "grad_norm": 7.110604763031006,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.2156,
+      "step": 51
+    },
+    {
+      "epoch": 0.46068660022148394,
+      "grad_norm": 11.897268295288086,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 2.9007,
+      "step": 52
+    },
+    {
+      "epoch": 0.4695459579180509,
+      "grad_norm": 13.057817459106445,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 2.002,
+      "step": 53
+    },
+    {
+      "epoch": 0.47840531561461797,
+      "grad_norm": 33.48012924194336,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.78,
+      "step": 54
+    },
+    {
+      "epoch": 0.48726467331118495,
+      "grad_norm": 12.036636352539062,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.3839,
+      "step": 55
+    },
+    {
+      "epoch": 0.49612403100775193,
+      "grad_norm": 14.421751976013184,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 2.0987,
+      "step": 56
+    },
+    {
+      "epoch": 0.5049833887043189,
+      "grad_norm": 4.778162002563477,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4264,
+      "step": 57
+    },
+    {
+      "epoch": 0.5138427464008859,
+      "grad_norm": 4.118379592895508,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.6587,
+      "step": 58
+    },
+    {
+      "epoch": 0.5227021040974529,
+      "grad_norm": 5.660857677459717,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.4942,
+      "step": 59
+    },
+    {
+      "epoch": 0.53156146179402,
+      "grad_norm": 6.020554065704346,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.3698,
+      "step": 60
+    },
+    {
+      "epoch": 0.540420819490587,
+      "grad_norm": 4.333651065826416,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 1.0231,
+      "step": 61
+    },
+    {
+      "epoch": 0.5492801771871539,
+      "grad_norm": 4.257166862487793,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.7315,
+      "step": 62
+    },
+    {
+      "epoch": 0.5581395348837209,
+      "grad_norm": 4.766343593597412,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9981,
+      "step": 63
+    },
+    {
+      "epoch": 0.5669988925802879,
+      "grad_norm": 6.86870002746582,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 1.755,
+      "step": 64
+    },
+    {
+      "epoch": 0.5758582502768549,
+      "grad_norm": 5.589112758636475,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 1.2156,
+      "step": 65
+    },
+    {
+      "epoch": 0.584717607973422,
+      "grad_norm": 4.641630172729492,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0218,
+      "step": 66
+    },
+    {
+      "epoch": 0.593576965669989,
+      "grad_norm": 4.352156162261963,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.7238,
+      "step": 67
+    },
+    {
+      "epoch": 0.602436323366556,
+      "grad_norm": 6.274971961975098,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 1.115,
+      "step": 68
+    },
+    {
+      "epoch": 0.6112956810631229,
+      "grad_norm": 4.748111248016357,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8593,
+      "step": 69
+    },
+    {
+      "epoch": 0.6201550387596899,
+      "grad_norm": 7.396561622619629,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 1.2128,
+      "step": 70
+    },
+    {
+      "epoch": 0.6290143964562569,
+      "grad_norm": 9.86874008178711,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.2177,
+      "step": 71
+    },
+    {
+      "epoch": 0.6378737541528239,
+      "grad_norm": 8.11063003540039,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.5982,
+      "step": 72
+    },
+    {
+      "epoch": 0.646733111849391,
+      "grad_norm": 7.7454729080200195,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 1.5252,
+      "step": 73
+    },
+    {
+      "epoch": 0.655592469545958,
+      "grad_norm": 6.750486850738525,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 1.6062,
+      "step": 74
+    },
+    {
+      "epoch": 0.6644518272425249,
+      "grad_norm": 12.320877075195312,
+      "learning_rate": 0.0,
+      "loss": 2.2862,
+      "step": 75
+    },
+    {
+      "epoch": 0.6644518272425249,
+      "eval_loss": 0.16002579033374786,
+      "eval_runtime": 33.0878,
+      "eval_samples_per_second": 2.871,
+      "eval_steps_per_second": 1.451,
+      "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": 7.07252667285504e+16,
+  "total_flos": 1.060879000928256e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null