Training in progress, step 140000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeef6904cfa32f848b9f1346c4e3c74b0fca915a351a8997e9e3c00ba9dcbbc5
+oid sha256:541c09487d9370b723d6f46473ad77d95854f9f277155774d36540daed587c20
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd16d9355565127d935e0581e06272701548caedebf90cbf8e7ec4700d308c92
+oid sha256:29c9ea605b07acd9d6d6f974a1449b64b38a1f91d2d0376e5cf078cd024be1d7
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c3369fb2b68cab39ce1c39a70e82cbae407ebef20a3614cae5eb0b8e29d67bb
-size 14503
+oid sha256:b84e894ef7a6033cd0e73130f2ebea7e9ec1ffbcfd8c8b79709a364acfd0ff22
+size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adc589057b5ab70a677240ea7ff1b31050aa971f7175362abbce011dcf3e27e4
+oid sha256:846e21193961d3c01650602fd61d067e6d15bb106fa27a0a886ebc7bc071a463
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a41a3d1e1a810c6ca0c122b02d703e10618433c01e7c57fdc5c7f1070e2b8072
-size 14503
+oid sha256:3963fd41f8e5a2e50a3c7c43d6a3b5ff095e754a9f186db5cd3c2302fcde5d99
+size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1078dca16195c4c6a10dd246658bec7f4ef493b51f155eaecbd40e7b74829373
+oid sha256:14ea5cea28ed719f191afec655c9dab07c0fb35f9db9c4929b4e91078fef40d5
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0714a313dd4ce4e99c82bf70e5eccb41f6003fe208bd22b2e683fd5e729c762a
+oid sha256:b5024aa92c1c16069c6562483f940b6c61d0a6604a0773cc4bdb5211b70f77f4
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9851268190633256,
-  "global_step": 130000,
+  "epoch": 2.1378288820681965,
+  "global_step": 140000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -968,11 +968,85 @@
       "eval_samples_per_second": 991.553,
       "eval_steps_per_second": 15.865,
       "step": 130000
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00014750372550514533,
+      "loss": 0.3409,
+      "step": 131000
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.0001474420890809492,
+      "loss": 0.3401,
+      "step": 132000
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.00014737971512087202,
+      "loss": 0.3396,
+      "step": 133000
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 0.00014731660430702552,
+      "loss": 0.339,
+      "step": 134000
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.00014725275732957937,
+      "loss": 0.3402,
+      "step": 135000
+    },
+    {
+      "epoch": 2.06,
+      "eval_runtime": 1.1005,
+      "eval_samples_per_second": 908.652,
+      "eval_steps_per_second": 14.538,
+      "step": 135000
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 0.00014718817488675387,
+      "loss": 0.3379,
+      "step": 136000
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.00014712285768481235,
+      "loss": 0.3371,
+      "step": 137000
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.00014705680643805323,
+      "loss": 0.3368,
+      "step": 138000
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 0.00014699002186880232,
+      "loss": 0.3363,
+      "step": 139000
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.00014692250470740503,
+      "loss": 0.3361,
+      "step": 140000
+    },
+    {
+      "epoch": 2.14,
+      "eval_runtime": 1.0104,
+      "eval_samples_per_second": 989.716,
+      "eval_steps_per_second": 15.835,
+      "step": 140000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 9.113027363263641e+21,
+  "total_flos": 9.814023402885625e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd16d9355565127d935e0581e06272701548caedebf90cbf8e7ec4700d308c92
+oid sha256:29c9ea605b07acd9d6d6f974a1449b64b38a1f91d2d0376e5cf078cd024be1d7
 size 449471589