Training in progress, step 70000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b25ce26c4c4eb983ffdc2bc9c7b644b728aef230ff82ddd8a2030da415dbb2b
-size 202193937
+oid sha256:f4b0acd993b58e7380979a32d60d902e29b0237163228000964967ed569f4694
+size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:421173a6d0b779538ba1088b472ee8a48ec34ebc9c6001dc0452a17c3f898cd8
+oid sha256:cb6589d1615ce90e186fa8aa811fe1eac2541e5dd82ff7b826939fd09b74c6d4
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f33b70beca1886b10946b4490286392efe66be8b967215ba0c867e43d6596b
+oid sha256:a5ed4685eb70c7ec28dbbc2df9e1ee4ad1f5e90711949c400c4e8797ccd59493
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f33b70beca1886b10946b4490286392efe66be8b967215ba0c867e43d6596b
+oid sha256:a5ed4685eb70c7ec28dbbc2df9e1ee4ad1f5e90711949c400c4e8797ccd59493
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f33b70beca1886b10946b4490286392efe66be8b967215ba0c867e43d6596b
+oid sha256:a5ed4685eb70c7ec28dbbc2df9e1ee4ad1f5e90711949c400c4e8797ccd59493
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f33b70beca1886b10946b4490286392efe66be8b967215ba0c867e43d6596b
+oid sha256:a5ed4685eb70c7ec28dbbc2df9e1ee4ad1f5e90711949c400c4e8797ccd59493
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f33b70beca1886b10946b4490286392efe66be8b967215ba0c867e43d6596b
+oid sha256:a5ed4685eb70c7ec28dbbc2df9e1ee4ad1f5e90711949c400c4e8797ccd59493
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f33b70beca1886b10946b4490286392efe66be8b967215ba0c867e43d6596b
+oid sha256:a5ed4685eb70c7ec28dbbc2df9e1ee4ad1f5e90711949c400c4e8797ccd59493
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f33b70beca1886b10946b4490286392efe66be8b967215ba0c867e43d6596b
+oid sha256:a5ed4685eb70c7ec28dbbc2df9e1ee4ad1f5e90711949c400c4e8797ccd59493
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f33b70beca1886b10946b4490286392efe66be8b967215ba0c867e43d6596b
+oid sha256:a5ed4685eb70c7ec28dbbc2df9e1ee4ad1f5e90711949c400c4e8797ccd59493
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1afd4be721b18cec2bad25f6a60e1c3abb5c311277f62eb3e2f010bc31239df1
+oid sha256:c6a21aa935b59f32e80e60eb114e1441ce82daea46fee66d7b5b4fedbaaa6094
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3979822456254807,
-  "global_step": 60000,
+  "epoch": 1.6309792865630608,
+  "global_step": 70000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1206,11 +1206,211 @@
       "eval_samples_per_second": 1536.88,
       "eval_steps_per_second": 24.473,
       "step": 60000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00029602157489814693,
+      "loss": 0.3234,
+      "step": 60500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00029590925100598365,
+      "loss": 0.3229,
+      "step": 61000
+    },
+    {
+      "epoch": 1.42,
+      "eval_loss": 0.3047891855239868,
+      "eval_runtime": 1.4211,
+      "eval_samples_per_second": 1546.647,
+      "eval_steps_per_second": 24.628,
+      "step": 61000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.000295795386152827,
+      "loss": 0.323,
+      "step": 61500
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.0002956799815838848,
+      "loss": 0.3223,
+      "step": 62000
+    },
+    {
+      "epoch": 1.44,
+      "eval_loss": 0.30619609355926514,
+      "eval_runtime": 1.3977,
+      "eval_samples_per_second": 1572.599,
+      "eval_steps_per_second": 25.041,
+      "step": 62000
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0002955630385612029,
+      "loss": 0.3217,
+      "step": 62500
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0002954445583636515,
+      "loss": 0.3215,
+      "step": 63000
+    },
+    {
+      "epoch": 1.47,
+      "eval_loss": 0.3042140007019043,
+      "eval_runtime": 1.3779,
+      "eval_samples_per_second": 1595.193,
+      "eval_steps_per_second": 25.401,
+      "step": 63000
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00029532454228691103,
+      "loss": 0.3212,
+      "step": 63500
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.0002952029916434581,
+      "loss": 0.3208,
+      "step": 64000
+    },
+    {
+      "epoch": 1.49,
+      "eval_loss": 0.30290499329566956,
+      "eval_runtime": 1.3826,
+      "eval_samples_per_second": 1589.79,
+      "eval_steps_per_second": 25.315,
+      "step": 64000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00029507990776255107,
+      "loss": 0.3206,
+      "step": 64500
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00029495529199021555,
+      "loss": 0.3201,
+      "step": 65000
+    },
+    {
+      "epoch": 1.51,
+      "eval_loss": 0.30093201994895935,
+      "eval_runtime": 1.3496,
+      "eval_samples_per_second": 1628.653,
+      "eval_steps_per_second": 25.934,
+      "step": 65000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.0002948291456892296,
+      "loss": 0.3199,
+      "step": 65500
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00029470147023910907,
+      "loss": 0.3198,
+      "step": 66000
+    },
+    {
+      "epoch": 1.54,
+      "eval_loss": 0.3037390410900116,
+      "eval_runtime": 1.4125,
+      "eval_samples_per_second": 1556.101,
+      "eval_steps_per_second": 24.779,
+      "step": 66000
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0002945722670360921,
+      "loss": 0.3189,
+      "step": 66500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0002944415374931243,
+      "loss": 0.3187,
+      "step": 67000
+    },
+    {
+      "epoch": 1.56,
+      "eval_loss": 0.30209919810295105,
+      "eval_runtime": 1.3711,
+      "eval_samples_per_second": 1603.144,
+      "eval_steps_per_second": 25.528,
+      "step": 67000
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00029430928303984295,
+      "loss": 0.3184,
+      "step": 67500
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.0002941755051225616,
+      "loss": 0.3179,
+      "step": 68000
+    },
+    {
+      "epoch": 1.58,
+      "eval_loss": 0.29896965622901917,
+      "eval_runtime": 1.5715,
+      "eval_samples_per_second": 1398.699,
+      "eval_steps_per_second": 22.272,
+      "step": 68000
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00029404020520425417,
+      "loss": 0.3177,
+      "step": 68500
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.0002939033847645388,
+      "loss": 0.3176,
+      "step": 69000
+    },
+    {
+      "epoch": 1.61,
+      "eval_loss": 0.30087536573410034,
+      "eval_runtime": 1.4497,
+      "eval_samples_per_second": 1516.182,
+      "eval_steps_per_second": 24.143,
+      "step": 69000
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00029376504529966195,
+      "loss": 0.3172,
+      "step": 69500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00029362518832248184,
+      "loss": 0.3169,
+      "step": 70000
+    },
+    {
+      "epoch": 1.63,
+      "eval_loss": 0.3002066910266876,
+      "eval_runtime": 1.4297,
+      "eval_samples_per_second": 1537.403,
+      "eval_steps_per_second": 24.481,
+      "step": 70000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.9169203356560932e+21,
+  "total_flos": 2.2364074744305932e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:421173a6d0b779538ba1088b472ee8a48ec34ebc9c6001dc0452a17c3f898cd8
+oid sha256:cb6589d1615ce90e186fa8aa811fe1eac2541e5dd82ff7b826939fd09b74c6d4
 size 102501541