Training in progress, step 210000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67589357f5095310d4686130056aa06ce9ae4e2fa5ce926bd48f51088af92af7
+oid sha256:6726cc29ffbd179a11fbc16d86e9b622977d56af7affe8432ce17ac7f0c3324c
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f8355919230d3848ec5ca15fcb85fb31871fa61b50484347e59854072226bac
+oid sha256:25943354903cd35afbe5a9d2bfdd9b41bedaf40773891780d5be2bd5e21bdecd
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56696dbd8b022c9a375dc483a2ed57d389284babd22e89c40b8de9038eb3703d
+oid sha256:f03fb7438c7a7d082a41521ad34b09e54c24c6f0ce434446a8cee447a9825e2b
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c18c513645e98f74c56b9e9e177b503e18704a58f67fc3838ebaa773205ef1
+oid sha256:bc9d9f513ad52cd61a225040b44572cf8ad6a7b8c109e5c0f358d82b01eeccf1
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7657a362d765d540acd9b7e721a68b7cd2eb75cf243194edc5a268c52185c5f
+oid sha256:2a9d3b6fefa1771a4c0591688a8a75e14c07fabc888c3cb2da62c9a866f74518
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17cd85c4bd32b953041cb6ed12687d174e095b2b2edce062be3f66f2a0041ec7
+oid sha256:81ca6dfbee96ec9e54db682b05df0c1c63341958079572fddfe5a0fdd3446e54
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82157ec414d7845758afa3fc7a8ceafcaf8d618c9a8c5350ea190a69bffb0ab4
+oid sha256:300ca51e5088cb48f99d1cdf1919949938caf62a53f95795867484c1a5c8ec3a
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.054041260097424,
-  "global_step": 200000,
+  "epoch": 3.206743323102295,
+  "global_step": 210000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1486,11 +1486,85 @@
       "eval_samples_per_second": 881.333,
       "eval_steps_per_second": 14.101,
       "step": 200000
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 0.00014145265111193583,
+      "loss": 0.3121,
+      "step": 201000
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 0.00014134146760307043,
+      "loss": 0.3122,
+      "step": 202000
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 0.00014122961327374313,
+      "loss": 0.3131,
+      "step": 203000
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 0.0001411170893471749,
+      "loss": 0.3116,
+      "step": 204000
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 0.00014100389705390938,
+      "loss": 0.311,
+      "step": 205000
+    },
+    {
+      "epoch": 3.13,
+      "eval_runtime": 1.1239,
+      "eval_samples_per_second": 889.731,
+      "eval_steps_per_second": 14.236,
+      "step": 205000
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 0.0001408900376317994,
+      "loss": 0.311,
+      "step": 206000
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 0.0001407755123259933,
+      "loss": 0.3108,
+      "step": 207000
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 0.00014066032238892152,
+      "loss": 0.3104,
+      "step": 208000
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 0.00014054446908028272,
+      "loss": 0.3102,
+      "step": 209000
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 0.00014042795366703018,
+      "loss": 0.3097,
+      "step": 210000
+    },
+    {
+      "epoch": 3.21,
+      "eval_runtime": 1.0233,
+      "eval_samples_per_second": 977.233,
+      "eval_steps_per_second": 15.636,
+      "step": 210000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 1.4020032494024966e+22,
+  "total_flos": 1.4721035104328438e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f8355919230d3848ec5ca15fcb85fb31871fa61b50484347e59854072226bac
+oid sha256:25943354903cd35afbe5a9d2bfdd9b41bedaf40773891780d5be2bd5e21bdecd
 size 449471589