Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3ff95a4a44d74accc21047ab370d8017ebde971c734343bf11827f79f3d0aa1
+oid sha256:91660599b3077ad1745732e80389c0416616cc7517c50a554c407fe06bce1643
 size 904009512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa5691e5de1c2ffdcdeb0af1aa03c70cf1086b75ffb011f0f320499c0c9373fd
+oid sha256:477890913dd59379fa51fdbcc844219c0cac53c13dc48295bb6501bcb465239b
 size 1808174394

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ec9c1445be0b55b92cf87051b6b197a5f45b675ec9c95cfe73b40b3a698350b
+oid sha256:c65d4cf9d6a73374dc90d734d4cf0727b5471f1cc4e735d53b23807c304c22ad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:238a3d9d5d27b062089474e3b1f179ee6b549591914241d9518f7417141f6938
+oid sha256:3a0213b99585fb590604f0f2d631130facda7981a07fff5f23620c8420e5cedf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.691973090171814,
-  "best_model_checkpoint": "./vietquill/checkpoint-3125",
-  "epoch": 1.0,
+  "best_metric": 0.6816325187683105,
+  "best_model_checkpoint": "./vietquill/checkpoint-6250",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 3125,
+  "global_step": 6250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -57,6 +57,56 @@
       "eval_samples_per_second": 264.545,
       "eval_steps_per_second": 8.465,
       "step": 3125
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.739039659500122,
+      "learning_rate": 3.1333333333333334e-05,
+      "loss": 0.5487,
+      "step": 3500
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.6791564226150513,
+      "learning_rate": 2.8666666666666668e-05,
+      "loss": 0.5273,
+      "step": 4000
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.7030389308929443,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 0.5231,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.8268135786056519,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.5201,
+      "step": 5000
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.5327303409576416,
+      "learning_rate": 2.0666666666666666e-05,
+      "loss": 0.5208,
+      "step": 5500
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 1.5141078233718872,
+      "learning_rate": 1.8e-05,
+      "loss": 0.5112,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6816325187683105,
+      "eval_runtime": 3.7827,
+      "eval_samples_per_second": 264.364,
+      "eval_steps_per_second": 8.46,
+      "step": 6250
     }
   ],
   "logging_steps": 500,
@@ -76,7 +126,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5708980224000000.0,
+  "total_flos": 1.1417960448e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null