Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01f02a6552ebf557c663261cde7e237513b533f9cc549a0a4e441821d246faa3
+oid sha256:2a751a165bf17614987ee30caba843bf951957ba5761cc1ce2081c7374c53074
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9735805862fcaf445077a15d872c7a340cd7e8ea695d46738281425d99ff7bc1
+oid sha256:7480e0708a0bb83f0630f8cb4be5db168c5200d77f56a0ec1bd890be73a54559
 size 2911851147

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+oid sha256:a8e2011629d8bed3ef560fa11175cac55684c4e12a72634bb24abf767b6c7399
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f77569c2e850b04af982cc8c1389f1430851448915c593b69e5da36ce05b71d7
+oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b61ed96b9f34f057dffa0bad8ef6959040ba1cfe848017506ba05f40fdaea76
+oid sha256:61361c878721548392539ed308adea82ec21fc99e9c9e2512a2e560c5477b77c
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 500,
-  "best_metric": 1.025797724723816,
-  "best_model_checkpoint": "./sft-out/checkpoint-500",
-  "epoch": 0.8840267418089397,
+  "best_global_step": 1000,
+  "best_metric": 0.9919272661209106,
+  "best_model_checkpoint": "./sft-out/checkpoint-1000",
+  "epoch": 1.7673352118901597,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -86,6 +86,84 @@
       "eval_samples_per_second": 15.867,
       "eval_steps_per_second": 1.999,
       "step": 500
+    },
+    {
+      "epoch": 0.9724294159898337,
+      "grad_norm": 2.3597640991210938,
+      "learning_rate": 1.0034906514152239e-05,
+      "loss": 1.0521656036376954,
+      "step": 550
+    },
+    {
+      "epoch": 1.060113818443008,
+      "grad_norm": 2.0308382511138916,
+      "learning_rate": 8.297905008339677e-06,
+      "loss": 0.8026390075683594,
+      "step": 600
+    },
+    {
+      "epoch": 1.148516492623902,
+      "grad_norm": 2.3317034244537354,
+      "learning_rate": 6.612620797547087e-06,
+      "loss": 0.6939823150634765,
+      "step": 650
+    },
+    {
+      "epoch": 1.2369191668047959,
+      "grad_norm": 2.5876853466033936,
+      "learning_rate": 5.030260389724447e-06,
+      "loss": 0.6835686492919922,
+      "step": 700
+    },
+    {
+      "epoch": 1.3253218409856897,
+      "grad_norm": 2.342280149459839,
+      "learning_rate": 3.598903005150444e-06,
+      "loss": 0.6746553039550781,
+      "step": 750
+    },
+    {
+      "epoch": 1.4137245151665838,
+      "grad_norm": 2.354048728942871,
+      "learning_rate": 2.362039713653581e-06,
+      "loss": 0.6704821014404296,
+      "step": 800
+    },
+    {
+      "epoch": 1.502127189347478,
+      "grad_norm": 2.01891827583313,
+      "learning_rate": 1.3572519804629537e-06,
+      "loss": 0.6500045776367187,
+      "step": 850
+    },
+    {
+      "epoch": 1.5905298635283718,
+      "grad_norm": 2.010759115219116,
+      "learning_rate": 6.150697724044407e-07,
+      "loss": 0.6556130981445313,
+      "step": 900
+    },
+    {
+      "epoch": 1.6789325377092656,
+      "grad_norm": 2.3100311756134033,
+      "learning_rate": 1.580439203075812e-07,
+      "loss": 0.6622157287597656,
+      "step": 950
+    },
+    {
+      "epoch": 1.7673352118901597,
+      "grad_norm": 2.064932346343994,
+      "learning_rate": 6.092342209607083e-11,
+      "loss": 0.6651800537109375,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7673352118901597,
+      "eval_loss": 0.9919272661209106,
+      "eval_runtime": 31.6701,
+      "eval_samples_per_second": 15.788,
+      "eval_steps_per_second": 1.989,
+      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -100,12 +178,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.9429307822186496e+16,
+  "total_flos": 3.876769443016704e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null