Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2104c69c76bb5f7498e20e536872f422f030978404b94d89a9de441010a5a69
+oid sha256:d564790f12170e8eb3426162f97f210d011c0052f93d3536794c5fb4e973a8ac
 size 19744138

last-checkpoint/global_step1500/zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e4fc2954cc72af548664d80104267712968d8f24c344635ae6129899c7970de
+oid sha256:ef325bd41fc084d20dadef801e072a4ac2d89af12588e1ca3d08bc70e3b0a93f
 size 29495149

last-checkpoint/global_step1500/zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73ef8e42b87dcf95560f1c316b545e4ec9f260b52ad4d66ba4ef8413401db1d0
+oid sha256:a5373c6d0b6d8090728a9568fc9cbbb4d8a8166d7d3931c1cd8fec675d9a5667
 size 29495149

last-checkpoint/global_step1500/zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b2a1de6b973813c41c7c5ebeefa2b87fd159b170d4caacbeca84db64d8344ae
+oid sha256:8c0985b989ac9aab8b36becd33d9a7052e786e5d499e97153b60837ce7713a5e
 size 29495149

last-checkpoint/global_step1500/zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2d5206daedb91f73077aecacd50e94e2d6ab8af8cc257e5bfbe899664c7e77e
+oid sha256:e157f34028cc9ae9977ed3b9ea517de8f0c6b55bbac619b5b3a332f52a9b4606
 size 29495149

last-checkpoint/latest

@@ -1 +1 @@
-global_step1000
+global_step1500

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e8728622af315db29b20e7895285cdcf395df663817cbd8286e8a542da77a9e
+oid sha256:aae6d6720b15d33c5be4514b3a84567730795fd13a72414380b33c8627313482
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abcaf5452298de0401ff6275854839dac435f28b7ef9e373a40036dc3a2d0391
+oid sha256:21210fc84cdeb9ead738b46e656c45624567b9d572c3ad0ea9fa169dff66448e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95f0bdcdc9a519a9ba2d416e546cb553cfb5a5725027ca6027cc188c0e93d2da
+oid sha256:8694520fe08f7a3fe633f373a0dc945b74219cd9f27299648abfd33c17fb7442
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bf5603ebd4cae7ae6cdcd72b39a5bb65e2c71003884ab266de81eddf51ac20d
+oid sha256:20a9d6951e84f6da45adca2f04a48bf1d75088b7d2fe1a9040ff33c84bae9cfc
 size 15024

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.42158516020236086,
+  "epoch": 0.6323777403035413,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -607,13 +607,313 @@
       "learning_rate": 1e-05,
       "loss": 0.7154,
       "step": 1000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1e-05,
+      "loss": 0.7956,
+      "step": 1010
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1e-05,
+      "loss": 0.7585,
+      "step": 1020
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1e-05,
+      "loss": 0.6719,
+      "step": 1030
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1e-05,
+      "loss": 0.7522,
+      "step": 1040
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1e-05,
+      "loss": 0.6662,
+      "step": 1050
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1e-05,
+      "loss": 0.7183,
+      "step": 1060
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1e-05,
+      "loss": 0.7223,
+      "step": 1070
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1e-05,
+      "loss": 0.7465,
+      "step": 1080
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1e-05,
+      "loss": 0.7484,
+      "step": 1090
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1e-05,
+      "loss": 0.6895,
+      "step": 1100
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1e-05,
+      "loss": 0.6901,
+      "step": 1110
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1e-05,
+      "loss": 0.722,
+      "step": 1120
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1e-05,
+      "loss": 0.7205,
+      "step": 1130
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1e-05,
+      "loss": 0.7023,
+      "step": 1140
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1e-05,
+      "loss": 0.7362,
+      "step": 1150
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1e-05,
+      "loss": 0.7017,
+      "step": 1160
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1e-05,
+      "loss": 0.7371,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1e-05,
+      "loss": 0.6835,
+      "step": 1180
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1e-05,
+      "loss": 0.6932,
+      "step": 1190
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1e-05,
+      "loss": 0.709,
+      "step": 1200
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1e-05,
+      "loss": 0.7183,
+      "step": 1210
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1e-05,
+      "loss": 0.6728,
+      "step": 1220
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1e-05,
+      "loss": 0.7082,
+      "step": 1230
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1e-05,
+      "loss": 0.7386,
+      "step": 1240
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1e-05,
+      "loss": 0.7759,
+      "step": 1250
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1e-05,
+      "loss": 0.7074,
+      "step": 1260
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1e-05,
+      "loss": 0.7434,
+      "step": 1270
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1e-05,
+      "loss": 0.7182,
+      "step": 1280
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1e-05,
+      "loss": 0.7363,
+      "step": 1290
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1e-05,
+      "loss": 0.7298,
+      "step": 1300
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1e-05,
+      "loss": 0.7573,
+      "step": 1310
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1e-05,
+      "loss": 0.6634,
+      "step": 1320
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1e-05,
+      "loss": 0.7064,
+      "step": 1330
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1e-05,
+      "loss": 0.7203,
+      "step": 1340
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1e-05,
+      "loss": 0.7016,
+      "step": 1350
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1e-05,
+      "loss": 0.7063,
+      "step": 1360
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1e-05,
+      "loss": 0.7035,
+      "step": 1370
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1e-05,
+      "loss": 0.7432,
+      "step": 1380
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1e-05,
+      "loss": 0.6509,
+      "step": 1390
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1e-05,
+      "loss": 0.7226,
+      "step": 1400
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1e-05,
+      "loss": 0.6995,
+      "step": 1410
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1e-05,
+      "loss": 0.6947,
+      "step": 1420
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1e-05,
+      "loss": 0.7199,
+      "step": 1430
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1e-05,
+      "loss": 0.677,
+      "step": 1440
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1e-05,
+      "loss": 0.6938,
+      "step": 1450
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1e-05,
+      "loss": 0.7324,
+      "step": 1460
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1e-05,
+      "loss": 0.6413,
+      "step": 1470
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1e-05,
+      "loss": 0.7271,
+      "step": 1480
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1e-05,
+      "loss": 0.685,
+      "step": 1490
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1e-05,
+      "loss": 0.7034,
+      "step": 1500
     }
   ],
   "logging_steps": 10,
   "max_steps": 5000,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 251028716912640.0,
+  "total_flos": 376920751472640.0,
   "trial_name": null,
   "trial_params": null
 }