Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:304f17a2ba68401cb4af386029899e25044b90c23fccbaa0c7a46ca6f6b0d9eb
+oid sha256:185c86d03b8919d827cfda798d6fc29e1913cd864aa192b86e8491594b1d1b0f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45f2d8fddfca1915baa8119f7c5d4392fdf29bac2c975a1dbde171a1662cd7d9
+oid sha256:34c198334f6b7491854622a24f40ba33c28a5f0d45e246c26f9832c6beb92702
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5405a2426404a2c5cb0086cff428a4dbeac18de2745c08d30e74a7618d46a415
+oid sha256:302bdaa3631472c313ddd863eb469503588de271524ef76a74a82a7afa61fd40
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beb167787cdd9594eed637547cf4a56f4a4d8ea359757a120c76bb5d91190782
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1986754966887417,
+  "epoch": 0.26490066225165565,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 24.758,
       "eval_steps_per_second": 12.457,
       "step": 75
+    },
+    {
+      "epoch": 0.20132450331125828,
+      "grad_norm": 6.836699962615967,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 6.6397,
+      "step": 76
+    },
+    {
+      "epoch": 0.20397350993377483,
+      "grad_norm": 7.016422748565674,
+      "learning_rate": 3.053416295410026e-05,
+      "loss": 6.9548,
+      "step": 77
+    },
+    {
+      "epoch": 0.20662251655629138,
+      "grad_norm": 5.971282482147217,
+      "learning_rate": 2.8066019966134904e-05,
+      "loss": 6.9251,
+      "step": 78
+    },
+    {
+      "epoch": 0.20927152317880796,
+      "grad_norm": 5.713533878326416,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 6.7799,
+      "step": 79
+    },
+    {
+      "epoch": 0.2119205298013245,
+      "grad_norm": 6.973901748657227,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 6.9072,
+      "step": 80
+    },
+    {
+      "epoch": 0.21456953642384105,
+      "grad_norm": 6.7183685302734375,
+      "learning_rate": 2.119892463932781e-05,
+      "loss": 6.9971,
+      "step": 81
+    },
+    {
+      "epoch": 0.21721854304635763,
+      "grad_norm": 6.681792259216309,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 7.233,
+      "step": 82
+    },
+    {
+      "epoch": 0.21986754966887417,
+      "grad_norm": 8.250860214233398,
+      "learning_rate": 1.7096242744495837e-05,
+      "loss": 7.0648,
+      "step": 83
+    },
+    {
+      "epoch": 0.22251655629139072,
+      "grad_norm": 6.514826774597168,
+      "learning_rate": 1.5195190384357404e-05,
+      "loss": 6.2877,
+      "step": 84
+    },
+    {
+      "epoch": 0.2251655629139073,
+      "grad_norm": 6.5112786293029785,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 6.7192,
+      "step": 85
+    },
+    {
+      "epoch": 0.22781456953642384,
+      "grad_norm": 6.814388751983643,
+      "learning_rate": 1.1705240714107302e-05,
+      "loss": 7.2217,
+      "step": 86
+    },
+    {
+      "epoch": 0.2304635761589404,
+      "grad_norm": 5.921008586883545,
+      "learning_rate": 1.0120595370083318e-05,
+      "loss": 7.1328,
+      "step": 87
+    },
+    {
+      "epoch": 0.23311258278145697,
+      "grad_norm": 5.6203932762146,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 5.9535,
+      "step": 88
+    },
+    {
+      "epoch": 0.23576158940397351,
+      "grad_norm": 6.021057605743408,
+      "learning_rate": 7.281614543321269e-06,
+      "loss": 6.8638,
+      "step": 89
+    },
+    {
+      "epoch": 0.23841059602649006,
+      "grad_norm": 7.241350173950195,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 7.3687,
+      "step": 90
+    },
+    {
+      "epoch": 0.2410596026490066,
+      "grad_norm": 6.832858562469482,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 6.4625,
+      "step": 91
+    },
+    {
+      "epoch": 0.24370860927152319,
+      "grad_norm": 6.067267894744873,
+      "learning_rate": 3.873830406168111e-06,
+      "loss": 6.7384,
+      "step": 92
+    },
+    {
+      "epoch": 0.24635761589403973,
+      "grad_norm": 7.329842567443848,
+      "learning_rate": 2.970427372400353e-06,
+      "loss": 6.5468,
+      "step": 93
+    },
+    {
+      "epoch": 0.24900662251655628,
+      "grad_norm": 5.869202136993408,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 7.0172,
+      "step": 94
+    },
+    {
+      "epoch": 0.25165562913907286,
+      "grad_norm": 5.81821870803833,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 6.985,
+      "step": 95
+    },
+    {
+      "epoch": 0.2543046357615894,
+      "grad_norm": 7.167514801025391,
+      "learning_rate": 9.731931258429638e-07,
+      "loss": 7.0374,
+      "step": 96
+    },
+    {
+      "epoch": 0.25695364238410595,
+      "grad_norm": 6.343252182006836,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 5.98,
+      "step": 97
+    },
+    {
+      "epoch": 0.2596026490066225,
+      "grad_norm": 6.643914222717285,
+      "learning_rate": 2.4359497401758024e-07,
+      "loss": 6.9213,
+      "step": 98
+    },
+    {
+      "epoch": 0.26225165562913905,
+      "grad_norm": 5.431641101837158,
+      "learning_rate": 6.09172980904238e-08,
+      "loss": 7.2081,
+      "step": 99
+    },
+    {
+      "epoch": 0.26490066225165565,
+      "grad_norm": 6.084027290344238,
+      "learning_rate": 0.0,
+      "loss": 6.7836,
+      "step": 100
+    },
+    {
+      "epoch": 0.26490066225165565,
+      "eval_loss": 1.736009955406189,
+      "eval_runtime": 6.4349,
+      "eval_samples_per_second": 24.709,
+      "eval_steps_per_second": 12.432,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -578,12 +761,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.4766242946613248e+16,
+  "total_flos": 2.002425230445773e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null