Upload trainer_state.json

trainer_state.json

@@ -1,121 +1,296 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.34285714285714286,
+  "epoch": 0.05714285714285714,
   "eval_steps": 500,
-  "global_step": 150,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.022857142857142857,
-      "grad_norm": 1.0595301389694214,
-      "learning_rate": 0.002,
-      "loss": 3.6082,
+      "epoch": 0.0014285714285714286,
+      "grad_norm": 0.8723945021629333,
+      "learning_rate": 0.0002,
+      "loss": 1.4591,
       "step": 10
     },
     {
-      "epoch": 0.045714285714285714,
-      "grad_norm": 0.2752091884613037,
-      "learning_rate": 0.002,
-      "loss": 1.5529,
+      "epoch": 0.002857142857142857,
+      "grad_norm": 0.6812328100204468,
+      "learning_rate": 0.0002,
+      "loss": 1.335,
       "step": 20
     },
     {
-      "epoch": 0.06857142857142857,
-      "grad_norm": 0.17800529301166534,
-      "learning_rate": 0.002,
-      "loss": 1.0928,
+      "epoch": 0.004285714285714286,
+      "grad_norm": 0.4533853232860565,
+      "learning_rate": 0.0002,
+      "loss": 1.2956,
       "step": 30
     },
     {
-      "epoch": 0.09142857142857143,
-      "grad_norm": 0.21639685332775116,
-      "learning_rate": 0.002,
-      "loss": 0.99,
+      "epoch": 0.005714285714285714,
+      "grad_norm": 0.5219816565513611,
+      "learning_rate": 0.0002,
+      "loss": 1.177,
       "step": 40
     },
     {
-      "epoch": 0.11428571428571428,
-      "grad_norm": 0.2555713951587677,
-      "learning_rate": 0.002,
-      "loss": 0.884,
+      "epoch": 0.007142857142857143,
+      "grad_norm": 0.6963663697242737,
+      "learning_rate": 0.0002,
+      "loss": 1.1449,
       "step": 50
     },
     {
-      "epoch": 0.13714285714285715,
-      "grad_norm": 0.1835678517818451,
-      "learning_rate": 0.002,
-      "loss": 1.2252,
+      "epoch": 0.008571428571428572,
+      "grad_norm": 0.59157794713974,
+      "learning_rate": 0.0002,
+      "loss": 1.1329,
       "step": 60
     },
     {
-      "epoch": 0.16,
-      "grad_norm": 0.23407411575317383,
-      "learning_rate": 0.002,
-      "loss": 1.0325,
+      "epoch": 0.01,
+      "grad_norm": 0.6530716419219971,
+      "learning_rate": 0.0002,
+      "loss": 1.0745,
       "step": 70
     },
     {
-      "epoch": 0.18285714285714286,
-      "grad_norm": 0.20827867090702057,
-      "learning_rate": 0.002,
-      "loss": 0.9401,
+      "epoch": 0.011428571428571429,
+      "grad_norm": 0.5379722714424133,
+      "learning_rate": 0.0002,
+      "loss": 1.0786,
       "step": 80
     },
     {
-      "epoch": 0.2057142857142857,
-      "grad_norm": 0.20146110653877258,
-      "learning_rate": 0.002,
-      "loss": 0.8852,
+      "epoch": 0.012857142857142857,
+      "grad_norm": 0.6812428832054138,
+      "learning_rate": 0.0002,
+      "loss": 1.1211,
       "step": 90
     },
     {
-      "epoch": 0.22857142857142856,
-      "grad_norm": 0.2659783661365509,
-      "learning_rate": 0.002,
-      "loss": 0.8176,
+      "epoch": 0.014285714285714285,
+      "grad_norm": 0.7551608681678772,
+      "learning_rate": 0.0002,
+      "loss": 0.936,
       "step": 100
     },
     {
-      "epoch": 0.25142857142857145,
-      "grad_norm": 0.20099078118801117,
-      "learning_rate": 0.002,
-      "loss": 1.1806,
+      "epoch": 0.015714285714285715,
+      "grad_norm": 0.6422017812728882,
+      "learning_rate": 0.0002,
+      "loss": 1.1515,
       "step": 110
     },
     {
-      "epoch": 0.2742857142857143,
-      "grad_norm": 0.18531735241413116,
-      "learning_rate": 0.002,
-      "loss": 0.9712,
+      "epoch": 0.017142857142857144,
+      "grad_norm": 0.4808028042316437,
+      "learning_rate": 0.0002,
+      "loss": 1.068,
       "step": 120
     },
     {
-      "epoch": 0.29714285714285715,
-      "grad_norm": 0.19588737189769745,
-      "learning_rate": 0.002,
-      "loss": 0.918,
+      "epoch": 0.018571428571428572,
+      "grad_norm": 0.4988093078136444,
+      "learning_rate": 0.0002,
+      "loss": 1.0567,
       "step": 130
     },
     {
-      "epoch": 0.32,
-      "grad_norm": 0.19109125435352325,
-      "learning_rate": 0.002,
-      "loss": 0.7857,
+      "epoch": 0.02,
+      "grad_norm": 0.5651537179946899,
+      "learning_rate": 0.0002,
+      "loss": 0.9769,
       "step": 140
     },
     {
-      "epoch": 0.34285714285714286,
-      "grad_norm": 0.2857687771320343,
-      "learning_rate": 0.002,
-      "loss": 0.7828,
+      "epoch": 0.02142857142857143,
+      "grad_norm": 0.7912259101867676,
+      "learning_rate": 0.0002,
+      "loss": 0.8673,
       "step": 150
+    },
+    {
+      "epoch": 0.022857142857142857,
+      "grad_norm": 0.6468149423599243,
+      "learning_rate": 0.0002,
+      "loss": 1.1511,
+      "step": 160
+    },
+    {
+      "epoch": 0.024285714285714285,
+      "grad_norm": 0.5371859669685364,
+      "learning_rate": 0.0002,
+      "loss": 1.0232,
+      "step": 170
+    },
+    {
+      "epoch": 0.025714285714285714,
+      "grad_norm": 0.5603945255279541,
+      "learning_rate": 0.0002,
+      "loss": 1.0743,
+      "step": 180
+    },
+    {
+      "epoch": 0.027142857142857142,
+      "grad_norm": 0.558032751083374,
+      "learning_rate": 0.0002,
+      "loss": 1.0368,
+      "step": 190
+    },
+    {
+      "epoch": 0.02857142857142857,
+      "grad_norm": 0.6991172432899475,
+      "learning_rate": 0.0002,
+      "loss": 0.9307,
+      "step": 200
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.4212726652622223,
+      "learning_rate": 0.0002,
+      "loss": 0.9608,
+      "step": 210
+    },
+    {
+      "epoch": 0.03142857142857143,
+      "grad_norm": 0.5686449408531189,
+      "learning_rate": 0.0002,
+      "loss": 1.0988,
+      "step": 220
+    },
+    {
+      "epoch": 0.032857142857142856,
+      "grad_norm": 0.5314635038375854,
+      "learning_rate": 0.0002,
+      "loss": 0.9674,
+      "step": 230
+    },
+    {
+      "epoch": 0.03428571428571429,
+      "grad_norm": 1.0691275596618652,
+      "learning_rate": 0.0002,
+      "loss": 0.9617,
+      "step": 240
+    },
+    {
+      "epoch": 0.03571428571428571,
+      "grad_norm": 0.3752906918525696,
+      "learning_rate": 0.0002,
+      "loss": 0.8711,
+      "step": 250
+    },
+    {
+      "epoch": 0.037142857142857144,
+      "grad_norm": 0.668821394443512,
+      "learning_rate": 0.0002,
+      "loss": 0.8694,
+      "step": 260
+    },
+    {
+      "epoch": 0.03857142857142857,
+      "grad_norm": 0.7953740358352661,
+      "learning_rate": 0.0002,
+      "loss": 0.9395,
+      "step": 270
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.4894189238548279,
+      "learning_rate": 0.0002,
+      "loss": 1.0876,
+      "step": 280
+    },
+    {
+      "epoch": 0.041428571428571426,
+      "grad_norm": 0.6148614287376404,
+      "learning_rate": 0.0002,
+      "loss": 1.0807,
+      "step": 290
+    },
+    {
+      "epoch": 0.04285714285714286,
+      "grad_norm": 0.5681003332138062,
+      "learning_rate": 0.0002,
+      "loss": 0.9068,
+      "step": 300
+    },
+    {
+      "epoch": 0.04428571428571428,
+      "grad_norm": 0.6531659960746765,
+      "learning_rate": 0.0002,
+      "loss": 0.9016,
+      "step": 310
+    },
+    {
+      "epoch": 0.045714285714285714,
+      "grad_norm": 0.46772944927215576,
+      "learning_rate": 0.0002,
+      "loss": 0.9432,
+      "step": 320
+    },
+    {
+      "epoch": 0.047142857142857146,
+      "grad_norm": 0.9201459884643555,
+      "learning_rate": 0.0002,
+      "loss": 0.9689,
+      "step": 330
+    },
+    {
+      "epoch": 0.04857142857142857,
+      "grad_norm": 0.4148743748664856,
+      "learning_rate": 0.0002,
+      "loss": 0.9866,
+      "step": 340
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.0026582479476929,
+      "learning_rate": 0.0002,
+      "loss": 1.0142,
+      "step": 350
+    },
+    {
+      "epoch": 0.05142857142857143,
+      "grad_norm": 0.5541752576828003,
+      "learning_rate": 0.0002,
+      "loss": 1.1917,
+      "step": 360
+    },
+    {
+      "epoch": 0.05285714285714286,
+      "grad_norm": 0.367127001285553,
+      "learning_rate": 0.0002,
+      "loss": 0.9925,
+      "step": 370
+    },
+    {
+      "epoch": 0.054285714285714284,
+      "grad_norm": 0.7337833046913147,
+      "learning_rate": 0.0002,
+      "loss": 0.9636,
+      "step": 380
+    },
+    {
+      "epoch": 0.055714285714285716,
+      "grad_norm": 0.8890251517295837,
+      "learning_rate": 0.0002,
+      "loss": 0.8888,
+      "step": 390
+    },
+    {
+      "epoch": 0.05714285714285714,
+      "grad_norm": 0.9325958490371704,
+      "learning_rate": 0.0002,
+      "loss": 0.746,
+      "step": 400
     }
   ],
   "logging_steps": 10,
-  "max_steps": 150,
+  "max_steps": 400,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
@@ -131,8 +306,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.524734837978624e+16,
-  "train_batch_size": 4,
+  "total_flos": 3002167578036480.0,
+  "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null
 }