checkpoint

{checkpoint-5404 → checkpoint-6562}/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7017270484352681,
+  "epoch": 0.8520971302428256,
   "eval_steps": 500,
-  "global_step": 5404,
+  "global_step": 6562,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -764,6 +764,167 @@
       "learning_rate": 1.742191816866202e-05,
       "loss": 0.1963,
       "step": 5400
+    },
+    {
+      "epoch": 0.7077002986625114,
+      "grad_norm": 0.8812252879142761,
+      "learning_rate": 1.7395605841336668e-05,
+      "loss": 0.196,
+      "step": 5450
+    },
+    {
+      "epoch": 0.7141929619529931,
+      "grad_norm": 0.6928241848945618,
+      "learning_rate": 1.7369293514011316e-05,
+      "loss": 0.2011,
+      "step": 5500
+    },
+    {
+      "epoch": 0.7206856252434749,
+      "grad_norm": 0.6892450451850891,
+      "learning_rate": 1.7342981186685965e-05,
+      "loss": 0.1949,
+      "step": 5550
+    },
+    {
+      "epoch": 0.7271782885339566,
+      "grad_norm": 0.4782065749168396,
+      "learning_rate": 1.7316668859360613e-05,
+      "loss": 0.194,
+      "step": 5600
+    },
+    {
+      "epoch": 0.7336709518244384,
+      "grad_norm": 0.6438505053520203,
+      "learning_rate": 1.729035653203526e-05,
+      "loss": 0.1967,
+      "step": 5650
+    },
+    {
+      "epoch": 0.7401636151149201,
+      "grad_norm": 0.5797818899154663,
+      "learning_rate": 1.726404420470991e-05,
+      "loss": 0.2185,
+      "step": 5700
+    },
+    {
+      "epoch": 0.7466562784054019,
+      "grad_norm": 0.6884586811065674,
+      "learning_rate": 1.7237731877384554e-05,
+      "loss": 0.1977,
+      "step": 5750
+    },
+    {
+      "epoch": 0.7531489416958836,
+      "grad_norm": 0.648883581161499,
+      "learning_rate": 1.7211419550059206e-05,
+      "loss": 0.1964,
+      "step": 5800
+    },
+    {
+      "epoch": 0.7596416049863655,
+      "grad_norm": 0.6440086960792542,
+      "learning_rate": 1.718510722273385e-05,
+      "loss": 0.2014,
+      "step": 5850
+    },
+    {
+      "epoch": 0.7661342682768472,
+      "grad_norm": 0.5619300007820129,
+      "learning_rate": 1.71587948954085e-05,
+      "loss": 0.1909,
+      "step": 5900
+    },
+    {
+      "epoch": 0.7726269315673289,
+      "grad_norm": 0.6859204769134521,
+      "learning_rate": 1.7132482568083147e-05,
+      "loss": 0.2049,
+      "step": 5950
+    },
+    {
+      "epoch": 0.7791195948578107,
+      "grad_norm": 0.6132592558860779,
+      "learning_rate": 1.7106170240757796e-05,
+      "loss": 0.2,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7856122581482924,
+      "grad_norm": 0.7050901055335999,
+      "learning_rate": 1.7079857913432444e-05,
+      "loss": 0.189,
+      "step": 6050
+    },
+    {
+      "epoch": 0.7921049214387742,
+      "grad_norm": 0.6752614974975586,
+      "learning_rate": 1.7053545586107092e-05,
+      "loss": 0.2248,
+      "step": 6100
+    },
+    {
+      "epoch": 0.7985975847292559,
+      "grad_norm": 0.7186923623085022,
+      "learning_rate": 1.702723325878174e-05,
+      "loss": 0.1903,
+      "step": 6150
+    },
+    {
+      "epoch": 0.8050902480197377,
+      "grad_norm": 0.5991400480270386,
+      "learning_rate": 1.700092093145639e-05,
+      "loss": 0.197,
+      "step": 6200
+    },
+    {
+      "epoch": 0.8115829113102194,
+      "grad_norm": 0.9522245526313782,
+      "learning_rate": 1.6974608604131037e-05,
+      "loss": 0.1962,
+      "step": 6250
+    },
+    {
+      "epoch": 0.8180755746007012,
+      "grad_norm": 0.8645381927490234,
+      "learning_rate": 1.6948296276805686e-05,
+      "loss": 0.1901,
+      "step": 6300
+    },
+    {
+      "epoch": 0.8245682378911829,
+      "grad_norm": 0.5243034958839417,
+      "learning_rate": 1.6921983949480334e-05,
+      "loss": 0.194,
+      "step": 6350
+    },
+    {
+      "epoch": 0.8310609011816648,
+      "grad_norm": 0.5842151641845703,
+      "learning_rate": 1.6895671622154982e-05,
+      "loss": 0.1917,
+      "step": 6400
+    },
+    {
+      "epoch": 0.8375535644721465,
+      "grad_norm": 0.6111485362052917,
+      "learning_rate": 1.6869359294829627e-05,
+      "loss": 0.2042,
+      "step": 6450
+    },
+    {
+      "epoch": 0.8440462277626283,
+      "grad_norm": 0.6515288949012756,
+      "learning_rate": 1.684304696750428e-05,
+      "loss": 0.2032,
+      "step": 6500
+    },
+    {
+      "epoch": 0.85053889105311,
+      "grad_norm": 0.7596396207809448,
+      "learning_rate": 1.6816734640178924e-05,
+      "loss": 0.193,
+      "step": 6550
     }
   ],
   "logging_steps": 50,
@@ -783,7 +944,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.519165203568394e+17,
+  "total_flos": 5.487557747765412e+17,
   "train_batch_size": 40,
   "trial_name": null,
   "trial_params": null