Training in progress, step 150000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:541c09487d9370b723d6f46473ad77d95854f9f277155774d36540daed587c20
+oid sha256:af89620dabb8befadb717e149645c7b1a4baa437ae00fe1a45d193867a75747e
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29c9ea605b07acd9d6d6f974a1449b64b38a1f91d2d0376e5cf078cd024be1d7
+oid sha256:a4473132994381129211918f004185b9788753aef90d5b6db4b7139479af4a5e
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b84e894ef7a6033cd0e73130f2ebea7e9ec1ffbcfd8c8b79709a364acfd0ff22
-size 14439
+oid sha256:6ce68a515967919f0a865a5bd2e1e8f70571d798e73f414abfc84271b022caff
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:846e21193961d3c01650602fd61d067e6d15bb106fa27a0a886ebc7bc071a463
+oid sha256:6380926153299d8b0e27207014365338e9fc035d7cd51dfa2b4a3c25b6edbff5
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3963fd41f8e5a2e50a3c7c43d6a3b5ff095e754a9f186db5cd3c2302fcde5d99
+oid sha256:77f61692f187e649a36856bc80d6adc9da2c6f8eb5a5983beddd87644fb8d73c
 size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ea5cea28ed719f191afec655c9dab07c0fb35f9db9c4929b4e91078fef40d5
-size 14503
+oid sha256:1f0c634c62ca05cfd25911633dd33cd6a1a4c0751ac34bfc4f130af2e87b7357
+size 14439

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5024aa92c1c16069c6562483f940b6c61d0a6604a0773cc4bdb5211b70f77f4
+oid sha256:6944aac36fb07ee223c68ca3cff3b6f262ad7e802285928ca04ff038bec935ea
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.1378288820681965,
-  "global_step": 140000,
+  "epoch": 2.2905309450730678,
+  "global_step": 150000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1042,11 +1042,85 @@
       "eval_samples_per_second": 989.716,
       "eval_steps_per_second": 15.835,
       "step": 140000
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 0.00014685425569221819,
+      "loss": 0.3353,
+      "step": 141000
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 0.00014678527556960207,
+      "loss": 0.3346,
+      "step": 142000
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 0.0001467155650939123,
+      "loss": 0.3342,
+      "step": 143000
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 0.00014664512502749141,
+      "loss": 0.3338,
+      "step": 144000
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 0.00014657395614066075,
+      "loss": 0.3334,
+      "step": 145000
+    },
+    {
+      "epoch": 2.21,
+      "eval_runtime": 1.0369,
+      "eval_samples_per_second": 964.439,
+      "eval_steps_per_second": 15.431,
+      "step": 145000
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 0.0001465020592117118,
+      "loss": 0.3327,
+      "step": 146000
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 0.0001464294350268979,
+      "loss": 0.3324,
+      "step": 147000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.00014635608438042546,
+      "loss": 0.3319,
+      "step": 148000
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 0.00014628200807444543,
+      "loss": 0.3313,
+      "step": 149000
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 0.0001462072069190444,
+      "loss": 0.3307,
+      "step": 150000
+    },
+    {
+      "epoch": 2.29,
+      "eval_runtime": 1.0431,
+      "eval_samples_per_second": 958.687,
+      "eval_steps_per_second": 15.339,
+      "step": 150000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 9.814023402885625e+21,
+  "total_flos": 1.0515026013189097e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29c9ea605b07acd9d6d6f974a1449b64b38a1f91d2d0376e5cf078cd024be1d7
+oid sha256:a4473132994381129211918f004185b9788753aef90d5b6db4b7139479af4a5e
 size 449471589