Training in progress, step 100000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f971e1495b95965474408a0b4cdd855e70f28b6c197542006f027ca89e6a9e5
+oid sha256:b4c86fed892e5d853a0aa10f530918fd27c33343c4e8c930c0a02ed36b9c3f12
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae321af5d431bdb16494979ea9657b4f788a7b917f7196ff1444688e31808017
+oid sha256:c1656fe19fa26589bb005c2ca1f054c8e8bb207866300c7f3b095bee470e6b55
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1986c24d7a3a4d6c5a8895904d8a1d8eb2f722e05eca51a88138a5893ec570fd
+oid sha256:ed45958fcf12318fa043e135a1ac933625a86df5477ef36cf136e443a8e9059f
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1986c24d7a3a4d6c5a8895904d8a1d8eb2f722e05eca51a88138a5893ec570fd
+oid sha256:ed45958fcf12318fa043e135a1ac933625a86df5477ef36cf136e443a8e9059f
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1986c24d7a3a4d6c5a8895904d8a1d8eb2f722e05eca51a88138a5893ec570fd
+oid sha256:ed45958fcf12318fa043e135a1ac933625a86df5477ef36cf136e443a8e9059f
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1986c24d7a3a4d6c5a8895904d8a1d8eb2f722e05eca51a88138a5893ec570fd
+oid sha256:ed45958fcf12318fa043e135a1ac933625a86df5477ef36cf136e443a8e9059f
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1986c24d7a3a4d6c5a8895904d8a1d8eb2f722e05eca51a88138a5893ec570fd
+oid sha256:ed45958fcf12318fa043e135a1ac933625a86df5477ef36cf136e443a8e9059f
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1986c24d7a3a4d6c5a8895904d8a1d8eb2f722e05eca51a88138a5893ec570fd
+oid sha256:ed45958fcf12318fa043e135a1ac933625a86df5477ef36cf136e443a8e9059f
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1986c24d7a3a4d6c5a8895904d8a1d8eb2f722e05eca51a88138a5893ec570fd
+oid sha256:ed45958fcf12318fa043e135a1ac933625a86df5477ef36cf136e443a8e9059f
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1986c24d7a3a4d6c5a8895904d8a1d8eb2f722e05eca51a88138a5893ec570fd
+oid sha256:ed45958fcf12318fa043e135a1ac933625a86df5477ef36cf136e443a8e9059f
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5810d5d1337eca8d561357c6c9e9920258e5fc2b2f0f70ea4b52e4984949eec8
+oid sha256:7786e0d240c1817a80f936fe537093f6b0f81238abcccea2c0e618f1ac9e9438
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.2936948876089507,
-  "global_step": 90000,
+  "epoch": 2.548549875121056,
+  "global_step": 100000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1806,11 +1806,211 @@
       "eval_samples_per_second": 813.129,
       "eval_steps_per_second": 13.01,
       "step": 90000
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.00028660537773622294,
+      "loss": 0.3158,
+      "step": 90500
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 0.00028640336867499143,
+      "loss": 0.3149,
+      "step": 91000
+    },
+    {
+      "epoch": 2.32,
+      "eval_loss": 0.8462135195732117,
+      "eval_runtime": 1.1973,
+      "eval_samples_per_second": 835.246,
+      "eval_steps_per_second": 13.364,
+      "step": 91000
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 0.0002861999226075728,
+      "loss": 0.3148,
+      "step": 91500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 0.0002859950417588206,
+      "loss": 0.3144,
+      "step": 92000
+    },
+    {
+      "epoch": 2.34,
+      "eval_loss": 0.8435172438621521,
+      "eval_runtime": 1.2492,
+      "eval_samples_per_second": 800.501,
+      "eval_steps_per_second": 12.808,
+      "step": 92000
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 0.00028578872836927904,
+      "loss": 0.3144,
+      "step": 92500
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 0.0002855809846951582,
+      "loss": 0.3141,
+      "step": 93000
+    },
+    {
+      "epoch": 2.37,
+      "eval_loss": 0.8363200426101685,
+      "eval_runtime": 1.2168,
+      "eval_samples_per_second": 821.803,
+      "eval_steps_per_second": 13.149,
+      "step": 93000
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 0.00028537181300830963,
+      "loss": 0.3138,
+      "step": 93500
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.0002851612155962014,
+      "loss": 0.3139,
+      "step": 94000
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.8434939384460449,
+      "eval_runtime": 1.2528,
+      "eval_samples_per_second": 798.238,
+      "eval_steps_per_second": 12.772,
+      "step": 94000
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 0.0002849491947618932,
+      "loss": 0.3139,
+      "step": 94500
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 0.0002847357528240107,
+      "loss": 0.3139,
+      "step": 95000
+    },
+    {
+      "epoch": 2.42,
+      "eval_loss": 0.8472431898117065,
+      "eval_runtime": 1.2611,
+      "eval_samples_per_second": 792.952,
+      "eval_steps_per_second": 12.687,
+      "step": 95000
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 0.0002845208921167208,
+      "loss": 0.3137,
+      "step": 95500
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 0.00028430461498970584,
+      "loss": 0.3131,
+      "step": 96000
+    },
+    {
+      "epoch": 2.45,
+      "eval_loss": 0.8395859599113464,
+      "eval_runtime": 1.2301,
+      "eval_samples_per_second": 812.96,
+      "eval_steps_per_second": 13.007,
+      "step": 96000
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 0.00028408692380813775,
+      "loss": 0.3125,
+      "step": 96500
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 0.00028386782095265247,
+      "loss": 0.3125,
+      "step": 97000
+    },
+    {
+      "epoch": 2.47,
+      "eval_loss": 0.8419870734214783,
+      "eval_runtime": 1.245,
+      "eval_samples_per_second": 803.234,
+      "eval_steps_per_second": 12.852,
+      "step": 97000
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 0.0002836473088193237,
+      "loss": 0.313,
+      "step": 97500
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 0.00028342538981963677,
+      "loss": 0.3128,
+      "step": 98000
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 0.8410093784332275,
+      "eval_runtime": 1.2759,
+      "eval_samples_per_second": 783.735,
+      "eval_steps_per_second": 12.54,
+      "step": 98000
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 0.0002832020663804624,
+      "loss": 0.3124,
+      "step": 98500
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 0.00028297734094402986,
+      "loss": 0.3121,
+      "step": 99000
+    },
+    {
+      "epoch": 2.52,
+      "eval_loss": 0.8417559862136841,
+      "eval_runtime": 1.2688,
+      "eval_samples_per_second": 788.14,
+      "eval_steps_per_second": 12.61,
+      "step": 99000
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 0.0002827512159679005,
+      "loss": 0.3122,
+      "step": 99500
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.00028252369392494086,
+      "loss": 0.3118,
+      "step": 100000
+    },
+    {
+      "epoch": 2.55,
+      "eval_loss": 0.8400096893310547,
+      "eval_runtime": 1.2486,
+      "eval_samples_per_second": 800.914,
+      "eval_steps_per_second": 12.815,
+      "step": 100000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 2.87535729114441e+21,
+  "total_flos": 3.19484442991891e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae321af5d431bdb16494979ea9657b4f788a7b917f7196ff1444688e31808017
+oid sha256:c1656fe19fa26589bb005c2ca1f054c8e8bb207866300c7f3b095bee470e6b55
 size 102501541