Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9b54ec1baff0ba606ce32e17ddc0f19455abd8192d57e00b521b66696511516
+oid sha256:114b891a762a51a9adf99795ed8a1397abbd097711bfd2ff3927ad599e912fbe
 size 3809184360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc1f0349be2c177d29c5468bf9f41d63cd942def1ae5e394f1fa17fe03d12a0
+oid sha256:0467314eaf329ce64fa294c5b636d1d0a5db236ce1684099429a56bad1f1c530
 size 2458291491

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74282f459a34ecd6a82ba47c711b2e80de77520f433252a7093c4336e7b2ec86
+oid sha256:0367ed1b35f65855ad993f74c56f185b353ad034ccb1dbb7df8ac313fc044216
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0269de58bb5fc10e493211ef487ccaef92d922164d165ce82302b7048ea90408
+oid sha256:5daf118c104c253ac47840aed00a104c21470bc6d0bd2a07133bec544d92037c
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7,
+  "epoch": 0.8,
   "eval_steps": 500,
-  "global_step": 1750,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1233,6 +1233,181 @@
       "learning_rate": 1.5221774193548388e-05,
       "loss": 0.6212,
       "step": 1750
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 6.325471878051758,
+      "learning_rate": 1.5020161290322581e-05,
+      "loss": 0.3136,
+      "step": 1760
+    },
+    {
+      "epoch": 0.708,
+      "grad_norm": 10.329962730407715,
+      "learning_rate": 1.4818548387096776e-05,
+      "loss": 0.4331,
+      "step": 1770
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 6.0466227531433105,
+      "learning_rate": 1.4616935483870969e-05,
+      "loss": 0.3234,
+      "step": 1780
+    },
+    {
+      "epoch": 0.716,
+      "grad_norm": 11.955286979675293,
+      "learning_rate": 1.4415322580645164e-05,
+      "loss": 0.3829,
+      "step": 1790
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 17.199453353881836,
+      "learning_rate": 1.4213709677419357e-05,
+      "loss": 0.5838,
+      "step": 1800
+    },
+    {
+      "epoch": 0.724,
+      "grad_norm": 7.430696964263916,
+      "learning_rate": 1.4012096774193548e-05,
+      "loss": 0.3352,
+      "step": 1810
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 18.183691024780273,
+      "learning_rate": 1.3810483870967741e-05,
+      "loss": 0.4604,
+      "step": 1820
+    },
+    {
+      "epoch": 0.732,
+      "grad_norm": 10.275338172912598,
+      "learning_rate": 1.3608870967741934e-05,
+      "loss": 0.3847,
+      "step": 1830
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 11.798257827758789,
+      "learning_rate": 1.340725806451613e-05,
+      "loss": 0.4413,
+      "step": 1840
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 9.844663619995117,
+      "learning_rate": 1.3205645161290322e-05,
+      "loss": 0.4583,
+      "step": 1850
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 11.413599967956543,
+      "learning_rate": 1.3004032258064517e-05,
+      "loss": 0.311,
+      "step": 1860
+    },
+    {
+      "epoch": 0.748,
+      "grad_norm": 14.305254936218262,
+      "learning_rate": 1.280241935483871e-05,
+      "loss": 0.3866,
+      "step": 1870
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 8.5895357131958,
+      "learning_rate": 1.2600806451612903e-05,
+      "loss": 0.4094,
+      "step": 1880
+    },
+    {
+      "epoch": 0.756,
+      "grad_norm": 14.033561706542969,
+      "learning_rate": 1.2399193548387098e-05,
+      "loss": 0.3887,
+      "step": 1890
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 9.73270034790039,
+      "learning_rate": 1.2197580645161291e-05,
+      "loss": 0.4129,
+      "step": 1900
+    },
+    {
+      "epoch": 0.764,
+      "grad_norm": 7.710170269012451,
+      "learning_rate": 1.1995967741935484e-05,
+      "loss": 0.2848,
+      "step": 1910
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 2.321779489517212,
+      "learning_rate": 1.1794354838709679e-05,
+      "loss": 0.2391,
+      "step": 1920
+    },
+    {
+      "epoch": 0.772,
+      "grad_norm": 7.158700466156006,
+      "learning_rate": 1.159274193548387e-05,
+      "loss": 0.3441,
+      "step": 1930
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 7.0267815589904785,
+      "learning_rate": 1.1391129032258065e-05,
+      "loss": 0.3391,
+      "step": 1940
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 8.56450080871582,
+      "learning_rate": 1.1189516129032258e-05,
+      "loss": 0.4174,
+      "step": 1950
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 13.748787879943848,
+      "learning_rate": 1.0987903225806453e-05,
+      "loss": 0.3004,
+      "step": 1960
+    },
+    {
+      "epoch": 0.788,
+      "grad_norm": 12.583123207092285,
+      "learning_rate": 1.0786290322580646e-05,
+      "loss": 0.3205,
+      "step": 1970
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 25.797645568847656,
+      "learning_rate": 1.0584677419354839e-05,
+      "loss": 0.327,
+      "step": 1980
+    },
+    {
+      "epoch": 0.796,
+      "grad_norm": 5.37972354888916,
+      "learning_rate": 1.0383064516129034e-05,
+      "loss": 0.3086,
+      "step": 1990
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 11.24709701538086,
+      "learning_rate": 1.0181451612903227e-05,
+      "loss": 0.2809,
+      "step": 2000
     }
   ],
   "logging_steps": 10,
@@ -1252,7 +1427,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.15998892642816e+16,
+  "total_flos": 3.61046831887872e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null