Training in progress, step 230000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62c0ec040ee2456e61ab40311e486f10de42e153791678bf443f54fc8893f828
+oid sha256:b9d08b16b8f0a6abe7e4ff06562f781b437ddd6c1464c0f95d747d51260c40e3
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:027aff93cad77a00849e3e1032a09ce43e2d9d45511b5e4cbbe8559338ed73ad
+oid sha256:cf594ad85da8b14fc79f1305a9d38a155ee31dc640b1cde587a09e1650e1b112
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff626d24667d1ce6888ac34600db16c7779e3e7daa61581a1c15d556bb284dd
+oid sha256:183346140573b10db5b967d424c726559ad36fe06d5946002c429fd0425a547c
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff626d24667d1ce6888ac34600db16c7779e3e7daa61581a1c15d556bb284dd
+oid sha256:183346140573b10db5b967d424c726559ad36fe06d5946002c429fd0425a547c
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff626d24667d1ce6888ac34600db16c7779e3e7daa61581a1c15d556bb284dd
+oid sha256:183346140573b10db5b967d424c726559ad36fe06d5946002c429fd0425a547c
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff626d24667d1ce6888ac34600db16c7779e3e7daa61581a1c15d556bb284dd
+oid sha256:183346140573b10db5b967d424c726559ad36fe06d5946002c429fd0425a547c
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff626d24667d1ce6888ac34600db16c7779e3e7daa61581a1c15d556bb284dd
+oid sha256:183346140573b10db5b967d424c726559ad36fe06d5946002c429fd0425a547c
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff626d24667d1ce6888ac34600db16c7779e3e7daa61581a1c15d556bb284dd
+oid sha256:183346140573b10db5b967d424c726559ad36fe06d5946002c429fd0425a547c
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff626d24667d1ce6888ac34600db16c7779e3e7daa61581a1c15d556bb284dd
+oid sha256:183346140573b10db5b967d424c726559ad36fe06d5946002c429fd0425a547c
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff626d24667d1ce6888ac34600db16c7779e3e7daa61581a1c15d556bb284dd
+oid sha256:183346140573b10db5b967d424c726559ad36fe06d5946002c429fd0425a547c
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a05d01a7b2f868e6f0e645a01ef2a1ba3ad5ea16b1bff8e9cf0cf653b106d64f
+oid sha256:2a2bb37359d05bc7917d91ab1261ba8c4d8f00648cd8cb2d11c677b6c91ddb27
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.606809725266324,
-  "global_step": 220000,
+  "epoch": 5.861664712778429,
+  "global_step": 230000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4406,11 +4406,211 @@
       "eval_samples_per_second": 800.922,
       "eval_steps_per_second": 12.815,
       "step": 220000
+    },
+    {
+      "epoch": 5.62,
+      "learning_rate": 0.00019476251528202922,
+      "loss": 0.2921,
+      "step": 220500
+    },
+    {
+      "epoch": 5.63,
+      "learning_rate": 0.0001943011739570944,
+      "loss": 0.2911,
+      "step": 221000
+    },
+    {
+      "epoch": 5.63,
+      "eval_loss": 0.8201115727424622,
+      "eval_runtime": 1.4717,
+      "eval_samples_per_second": 679.492,
+      "eval_steps_per_second": 10.872,
+      "step": 221000
+    },
+    {
+      "epoch": 5.65,
+      "learning_rate": 0.00019383940284081774,
+      "loss": 0.2912,
+      "step": 221500
+    },
+    {
+      "epoch": 5.66,
+      "learning_rate": 0.00019337720698305431,
+      "loss": 0.2913,
+      "step": 222000
+    },
+    {
+      "epoch": 5.66,
+      "eval_loss": 0.8082127571105957,
+      "eval_runtime": 1.2848,
+      "eval_samples_per_second": 778.358,
+      "eval_steps_per_second": 12.454,
+      "step": 222000
+    },
+    {
+      "epoch": 5.67,
+      "learning_rate": 0.0001929145914383038,
+      "loss": 0.2914,
+      "step": 222500
+    },
+    {
+      "epoch": 5.68,
+      "learning_rate": 0.00019245156126565586,
+      "loss": 0.2912,
+      "step": 223000
+    },
+    {
+      "epoch": 5.68,
+      "eval_loss": 0.8193914890289307,
+      "eval_runtime": 1.3731,
+      "eval_samples_per_second": 728.26,
+      "eval_steps_per_second": 11.652,
+      "step": 223000
+    },
+    {
+      "epoch": 5.7,
+      "learning_rate": 0.00019198812152873416,
+      "loss": 0.291,
+      "step": 223500
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 0.00019152427729564144,
+      "loss": 0.2908,
+      "step": 224000
+    },
+    {
+      "epoch": 5.71,
+      "eval_loss": 0.8259610533714294,
+      "eval_runtime": 1.2322,
+      "eval_samples_per_second": 811.569,
+      "eval_steps_per_second": 12.985,
+      "step": 224000
+    },
+    {
+      "epoch": 5.72,
+      "learning_rate": 0.00019106003363890395,
+      "loss": 0.2906,
+      "step": 224500
+    },
+    {
+      "epoch": 5.73,
+      "learning_rate": 0.00019059539563541584,
+      "loss": 0.291,
+      "step": 225000
+    },
+    {
+      "epoch": 5.73,
+      "eval_loss": 0.8225913643836975,
+      "eval_runtime": 1.2796,
+      "eval_samples_per_second": 781.52,
+      "eval_steps_per_second": 12.504,
+      "step": 225000
+    },
+    {
+      "epoch": 5.75,
+      "learning_rate": 0.000190130368366384,
+      "loss": 0.2908,
+      "step": 225500
+    },
+    {
+      "epoch": 5.76,
+      "learning_rate": 0.00018966495691727207,
+      "loss": 0.2908,
+      "step": 226000
+    },
+    {
+      "epoch": 5.76,
+      "eval_loss": 0.8231199979782104,
+      "eval_runtime": 1.2853,
+      "eval_samples_per_second": 778.049,
+      "eval_steps_per_second": 12.449,
+      "step": 226000
+    },
+    {
+      "epoch": 5.77,
+      "learning_rate": 0.0001891991663777451,
+      "loss": 0.2902,
+      "step": 226500
+    },
+    {
+      "epoch": 5.79,
+      "learning_rate": 0.00018873300184161387,
+      "loss": 0.2903,
+      "step": 227000
+    },
+    {
+      "epoch": 5.79,
+      "eval_loss": 0.8100917935371399,
+      "eval_runtime": 1.3376,
+      "eval_samples_per_second": 747.632,
+      "eval_steps_per_second": 11.962,
+      "step": 227000
+    },
+    {
+      "epoch": 5.8,
+      "learning_rate": 0.00018826646840677894,
+      "loss": 0.2902,
+      "step": 227500
+    },
+    {
+      "epoch": 5.81,
+      "learning_rate": 0.00018779957117517532,
+      "loss": 0.2917,
+      "step": 228000
+    },
+    {
+      "epoch": 5.81,
+      "eval_loss": 0.8147779107093811,
+      "eval_runtime": 1.2993,
+      "eval_samples_per_second": 769.654,
+      "eval_steps_per_second": 12.314,
+      "step": 228000
+    },
+    {
+      "epoch": 5.82,
+      "learning_rate": 0.00018733231525271625,
+      "loss": 0.2917,
+      "step": 228500
+    },
+    {
+      "epoch": 5.84,
+      "learning_rate": 0.00018686470574923766,
+      "loss": 0.2915,
+      "step": 229000
+    },
+    {
+      "epoch": 5.84,
+      "eval_loss": 0.8212478160858154,
+      "eval_runtime": 1.3093,
+      "eval_samples_per_second": 763.781,
+      "eval_steps_per_second": 12.22,
+      "step": 229000
+    },
+    {
+      "epoch": 5.85,
+      "learning_rate": 0.00018639674777844224,
+      "loss": 0.2903,
+      "step": 229500
+    },
+    {
+      "epoch": 5.86,
+      "learning_rate": 0.00018592844645784327,
+      "loss": 0.2901,
+      "step": 230000
+    },
+    {
+      "epoch": 5.86,
+      "eval_loss": 0.812626302242279,
+      "eval_runtime": 1.3081,
+      "eval_samples_per_second": 764.442,
+      "eval_steps_per_second": 12.231,
+      "step": 230000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 7.028649658473775e+21,
+  "total_flos": 7.348136797248275e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:027aff93cad77a00849e3e1032a09ce43e2d9d45511b5e4cbbe8559338ed73ad
+oid sha256:cf594ad85da8b14fc79f1305a9d38a155ee31dc640b1cde587a09e1650e1b112
 size 102501541