Training in progress, step 950000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a56a8f0ae8b5b9f2aec995742da47ff25dfe07ebb15ec7ee61db4a763d8289c8
+oid sha256:70e10dc58492fed71483adf6f5b8363903e23bef03e170ace087681ebc08713a
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c00c6557048c11e66b95589de29730bca35a40598e37017f064297cb592c4f93
+oid sha256:b779e5dbc65f9055978747a6483cc3aacc9d67baf238821e25b63cb286556c36
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e8be78115c1d7a8b7fd3ba012ea9e0890f7c8e7c74970d79909bd336b578ec4
+oid sha256:1c593a167703dbaf9947d32973b51a125779553f32e153671a91b63abf7f7876
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a534ad0e2fa8f314cc3ae9bccc570e59499e6b5c546b12853d32ae75d416e0e6
+oid sha256:d3c374b98251ab1768e65aa1b6a7f148a712a2ce1b1f2f903e4af64c54752379
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2825291049da8c0b63497c412e6d53ce0d529ebee7d30f4f47c2a1d271fc14d
-size 14503
+oid sha256:891f782320602223f61f367a6458f228c51432918fe313542e407d34511dfc6d
+size 14567

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:087eacd702285507c39ac952397dc9f6dae700c001504f218d7b716e9f249005
+oid sha256:9286b15801381b7a96fc2895ff30b4645bc69f0722e3eeae374fcb4eb7890f47
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dab84d4b75593cd9349f424c4371ea8ac2493751bc544a294c8ef74a18b08e9
+oid sha256:76d771b6aa86b6db5c1d3a18a5ba01d5f7ff8a339c98c29586734738700dc44c
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.353993922457892,
-  "global_step": 940000,
+  "epoch": 14.506695985462764,
+  "global_step": 950000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6962,11 +6962,85 @@
       "eval_samples_per_second": 1269.803,
       "eval_steps_per_second": 20.317,
       "step": 940000
+    },
+    {
+      "epoch": 14.37,
+      "learning_rate": 1.1328147928906494e-05,
+      "loss": 0.2287,
+      "step": 941000
+    },
+    {
+      "epoch": 14.38,
+      "learning_rate": 1.1283644453421678e-05,
+      "loss": 0.2289,
+      "step": 942000
+    },
+    {
+      "epoch": 14.4,
+      "learning_rate": 1.1239892448991798e-05,
+      "loss": 0.2284,
+      "step": 943000
+    },
+    {
+      "epoch": 14.42,
+      "learning_rate": 1.1196892394081743e-05,
+      "loss": 0.2287,
+      "step": 944000
+    },
+    {
+      "epoch": 14.43,
+      "learning_rate": 1.1154644758933235e-05,
+      "loss": 0.2285,
+      "step": 945000
+    },
+    {
+      "epoch": 14.43,
+      "eval_runtime": 0.7294,
+      "eval_samples_per_second": 1370.909,
+      "eval_steps_per_second": 21.935,
+      "step": 945000
+    },
+    {
+      "epoch": 14.45,
+      "learning_rate": 1.1113150005559644e-05,
+      "loss": 0.2283,
+      "step": 946000
+    },
+    {
+      "epoch": 14.46,
+      "learning_rate": 1.1072408587740942e-05,
+      "loss": 0.2282,
+      "step": 947000
+    },
+    {
+      "epoch": 14.48,
+      "learning_rate": 1.1032420951018755e-05,
+      "loss": 0.228,
+      "step": 948000
+    },
+    {
+      "epoch": 14.49,
+      "learning_rate": 1.0993187532691458e-05,
+      "loss": 0.2281,
+      "step": 949000
+    },
+    {
+      "epoch": 14.51,
+      "learning_rate": 1.0954708761809438e-05,
+      "loss": 0.2281,
+      "step": 950000
+    },
+    {
+      "epoch": 14.51,
+      "eval_runtime": 0.7692,
+      "eval_samples_per_second": 1300.007,
+      "eval_steps_per_second": 20.8,
+      "step": 950000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 6.589415337898549e+22,
+  "total_flos": 6.659515598928896e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c00c6557048c11e66b95589de29730bca35a40598e37017f064297cb592c4f93
+oid sha256:b779e5dbc65f9055978747a6483cc3aacc9d67baf238821e25b63cb286556c36
 size 449471589