Training in progress, step 190000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a7e34d71622ed2729105fb01520301222c71cea562f151f7179cc6bc4b9b50
+oid sha256:cd03613df05982cc6cd8521404bf2d7d311a82ab0ee46fc664ebdeffd43ec5fb
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30751dbb61ea71a9ce0a93f55b70e1a1196dfc0d7905f81e666b241fe83ddb77
+oid sha256:75854e0ff3e7c4405dc53eac04c2010a206af7aae27dae0d9ee35db9ad0a959a
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75d55dc4383f97263c7bbe8d3a50efcb2e3d7e3cace3b3db13ee7da25b48c2b4
+oid sha256:ed3586f2d8b7a9d0704645682c4f2d417639e4cca27eecf545ccb9e56c8d74df
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f3b1810a033427b234e2bffc73d00c710ede62d1be2ca4c7afaaf9e382d34f3
+oid sha256:38e985eb8bf02ef58974d91bc1d920b2617a41af091b03e6ddbcd3b7548fe4b3
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52c10056239563f1c1ae3a50f3e866a02915fb473e9e6b2140de76aa33912655
+oid sha256:2d738b37d6429a4b318ddcdaacb6b35096cf2474500c27a66a5a92064653d6fd
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15,
-  "global_step": 180000,
+  "epoch": 0.2,
+  "global_step": 190000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2454,11 +2454,147 @@
       "eval_samples_per_second": 148.965,
       "eval_steps_per_second": 2.328,
       "step": 180000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.2127388544199013e-05,
+      "loss": 0.378,
+      "step": 180500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.2020863570515961e-05,
+      "loss": 0.3783,
+      "step": 181000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.1917218873266704e-05,
+      "loss": 0.3774,
+      "step": 181500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.1816245104688946e-05,
+      "loss": 0.3768,
+      "step": 182000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.1717754173131136e-05,
+      "loss": 0.378,
+      "step": 182500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.162195718996353e-05,
+      "loss": 0.3775,
+      "step": 183000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.1528860064395268e-05,
+      "loss": 0.3778,
+      "step": 183500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.14384685390956e-05,
+      "loss": 0.377,
+      "step": 184000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.1350788189839584e-05,
+      "loss": 0.3769,
+      "step": 184500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.126582442516417e-05,
+      "loss": 0.3779,
+      "step": 185000
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.3469138443470001,
+      "eval_runtime": 287.4474,
+      "eval_samples_per_second": 149.593,
+      "eval_steps_per_second": 2.338,
+      "step": 185000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.1183582486034581e-05,
+      "loss": 0.3766,
+      "step": 185500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.1104067445521018e-05,
+      "loss": 0.3776,
+      "step": 186000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.102728420848572e-05,
+      "loss": 0.3772,
+      "step": 186500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.0953237511280449e-05,
+      "loss": 0.3769,
+      "step": 187000
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.0881931921454253e-05,
+      "loss": 0.3776,
+      "step": 187500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.0813506214785774e-05,
+      "loss": 0.3769,
+      "step": 188000
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.0747690362178142e-05,
+      "loss": 0.377,
+      "step": 188500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.0684628296065977e-05,
+      "loss": 0.3765,
+      "step": 189000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.0624323906414552e-05,
+      "loss": 0.376,
+      "step": 189500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.0566780913082688e-05,
+      "loss": 0.3777,
+      "step": 190000
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.34515419602394104,
+      "eval_runtime": 275.3559,
+      "eval_samples_per_second": 156.162,
+      "eval_steps_per_second": 2.44,
+      "step": 190000
     }
   ],
   "max_steps": 200000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 4.238875212565709e+21,
+  "total_flos": 4.4743682799304704e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30751dbb61ea71a9ce0a93f55b70e1a1196dfc0d7905f81e666b241fe83ddb77
+oid sha256:75854e0ff3e7c4405dc53eac04c2010a206af7aae27dae0d9ee35db9ad0a959a
 size 449471589