Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af81d9cc2f1ff0a05502e1f3c3b568e72183c6a9a6ed244129dfee78d5235ea3
+oid sha256:e047e722c8d2a4adc9591b035031716df14784019153e5c2953617fb6ea1cafb
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1458a837c7ed019986f54bcbb3f7348b1d0758cd92e5f2ade515474b8fa81142
+oid sha256:a5213051fb01503893c2fad99438564be3e49e499a49e491a435d2bf597ccf3f
 size 5365108834

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b318eb73ccb53da9f9ff5d08314f789cad6a3b7be48a96febfa65e8e395a406c
+oid sha256:a76bba0c9b8ac8dac910c8ef383772b76b506744638f9572748f5cedbdaa64b8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3329bd49914ec2503d9fec296dd4d936a9a9b917cb79af74aa9e6985885ffbb
+oid sha256:cc73dbb491eb6e262a9785fe01e1ee502ba913bf4d669672d7bd3a5646689cca
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49fd006ab5f700accd9b61a5a188065ff8d30a3bc36dad95368223dcd7a79350
+oid sha256:50c5b15cd9d3843fe6c13c787db34fa4f9c5781775a661a9a305d19a85a985bd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2adc11863e21cb21757bf05dae5c2c278dcd7ef8062ebb5e46e893344ad90d2d
+oid sha256:eaf7345f894543f3f7d3b26b10e54e981dfc4a90c5eb5fdea6e51da74075dfcf
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f1545021bacb1893e9a881b654d67556b0d7bb5407189283857b1e748411509
+oid sha256:794d9a4c9de1d78d0474fd1f61726dc1a90367d9a4ca4c964a2092e9c1a4b76b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07675232145791035,
+  "epoch": 0.11512848218686551,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,76 @@
       "learning_rate": 9.232422474669942e-05,
       "loss": 1.0674,
       "step": 1000
+    },
+    {
+      "epoch": 0.08058993753080586,
+      "grad_norm": 0.44129157066345215,
+      "learning_rate": 9.194043598403439e-05,
+      "loss": 1.0663,
+      "step": 1050
+    },
+    {
+      "epoch": 0.08442755360370138,
+      "grad_norm": 0.6179072856903076,
+      "learning_rate": 9.155664722136937e-05,
+      "loss": 1.0639,
+      "step": 1100
+    },
+    {
+      "epoch": 0.0882651696765969,
+      "grad_norm": 0.847963273525238,
+      "learning_rate": 9.117285845870434e-05,
+      "loss": 1.0601,
+      "step": 1150
+    },
+    {
+      "epoch": 0.09210278574949242,
+      "grad_norm": 0.8802704215049744,
+      "learning_rate": 9.07890696960393e-05,
+      "loss": 1.0536,
+      "step": 1200
+    },
+    {
+      "epoch": 0.09594040182238793,
+      "grad_norm": 0.837968111038208,
+      "learning_rate": 9.040528093337427e-05,
+      "loss": 1.0525,
+      "step": 1250
+    },
+    {
+      "epoch": 0.09977801789528346,
+      "grad_norm": 0.8432613611221313,
+      "learning_rate": 9.002149217070924e-05,
+      "loss": 1.0482,
+      "step": 1300
+    },
+    {
+      "epoch": 0.10361563396817897,
+      "grad_norm": 0.5921217799186707,
+      "learning_rate": 8.963770340804421e-05,
+      "loss": 1.0449,
+      "step": 1350
+    },
+    {
+      "epoch": 0.10745325004107449,
+      "grad_norm": 0.45630180835723877,
+      "learning_rate": 8.925391464537919e-05,
+      "loss": 1.0416,
+      "step": 1400
+    },
+    {
+      "epoch": 0.11129086611397,
+      "grad_norm": 0.45162612199783325,
+      "learning_rate": 8.887012588271416e-05,
+      "loss": 1.0384,
+      "step": 1450
+    },
+    {
+      "epoch": 0.11512848218686551,
+      "grad_norm": 0.9114300012588501,
+      "learning_rate": 8.848633712004914e-05,
+      "loss": 1.0355,
+      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -166,7 +236,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7142044867313009e+18,
+  "total_flos": 2.5713592704318833e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null