Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:690eff035cd63ee9b0fe22bcac27f83d2da7d1923cbcc5a1688b851e2c157372
+oid sha256:98d4561bb1c68228f9d4f30863f160d16adb444a259ac3ef92021f5cde965f6d
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46c116fe11cb2669559c3718e1ac0c09d5e0eeda64fe3e9a6b3ea9cdccdc9692
+oid sha256:6ad1682b7ea564f7d69311573185f4ed2c4052097ebfe75662195262add67e3c
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:525c858b82529418b224a8c411ffa1baf32c1afa45758860444bf9e713ff8c82
+oid sha256:a50e1949bc7c89cd8e26d0938c7aed1439c53347a58ebbc9f3c5eda1a643624b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aeda63dddeb04b23b8c70a9f0e46e303853eed00ecd067f9bb5ef2c82fb9752
+oid sha256:7ffa3a5db9e1f216274a290564548e9f5805d18ec3fa416d510dd4d711eeff27
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4545d4c2a647a7babebca0a95ff484abca47651bf5354ee370e9b70dc4b4d68c
+oid sha256:90be7c0097e0ebbce609fba45eca4e2a537c2f8870fbf114645260109731d37b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a8d5c93b8d1253e83039a044abc57770ce862a69073336786156bca7c933848
+oid sha256:00392d2ad320f5ff5044ef43a9b972336d103543ee1cf34fe382953d48d227ee
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3527735471725464,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03311532411623479,
+  "best_metric": 1.2570868730545044,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06623064823246957,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 48.516,
       "eval_steps_per_second": 6.067,
       "step": 25
+    },
+    {
+      "epoch": 0.03443993708088418,
+      "grad_norm": 0.928752064704895,
+      "learning_rate": 5e-05,
+      "loss": 1.1759,
+      "step": 26
+    },
+    {
+      "epoch": 0.03576455004553357,
+      "grad_norm": 1.1340597867965698,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.2971,
+      "step": 27
+    },
+    {
+      "epoch": 0.03708916301018296,
+      "grad_norm": 0.986423134803772,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.3528,
+      "step": 28
+    },
+    {
+      "epoch": 0.03841377597483235,
+      "grad_norm": 0.8538538813591003,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.2289,
+      "step": 29
+    },
+    {
+      "epoch": 0.03973838893948174,
+      "grad_norm": 0.7311115264892578,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.2389,
+      "step": 30
+    },
+    {
+      "epoch": 0.04106300190413114,
+      "grad_norm": 0.7120617032051086,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2412,
+      "step": 31
+    },
+    {
+      "epoch": 0.04238761486878053,
+      "grad_norm": 0.829824686050415,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1946,
+      "step": 32
+    },
+    {
+      "epoch": 0.04371222783342992,
+      "grad_norm": 0.8339101672172546,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.2097,
+      "step": 33
+    },
+    {
+      "epoch": 0.04503684079807931,
+      "grad_norm": 0.8611684441566467,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.1734,
+      "step": 34
+    },
+    {
+      "epoch": 0.046361453762728703,
+      "grad_norm": 0.807828426361084,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.0594,
+      "step": 35
+    },
+    {
+      "epoch": 0.047686066727378094,
+      "grad_norm": 1.0561130046844482,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.4825,
+      "step": 36
+    },
+    {
+      "epoch": 0.049010679692027485,
+      "grad_norm": 1.1005446910858154,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.5086,
+      "step": 37
+    },
+    {
+      "epoch": 0.050335292656676876,
+      "grad_norm": 0.780189573764801,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1526,
+      "step": 38
+    },
+    {
+      "epoch": 0.05165990562132627,
+      "grad_norm": 0.6735148429870605,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.3142,
+      "step": 39
+    },
+    {
+      "epoch": 0.05298451858597566,
+      "grad_norm": 0.8071457147598267,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.2842,
+      "step": 40
+    },
+    {
+      "epoch": 0.05430913155062505,
+      "grad_norm": 0.7985179424285889,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.209,
+      "step": 41
+    },
+    {
+      "epoch": 0.05563374451527444,
+      "grad_norm": 0.7388365268707275,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1442,
+      "step": 42
+    },
+    {
+      "epoch": 0.05695835747992384,
+      "grad_norm": 0.8493674993515015,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2623,
+      "step": 43
+    },
+    {
+      "epoch": 0.05828297044457323,
+      "grad_norm": 0.7348306179046631,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2582,
+      "step": 44
+    },
+    {
+      "epoch": 0.05960758340922262,
+      "grad_norm": 0.7038648724555969,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.1963,
+      "step": 45
+    },
+    {
+      "epoch": 0.06093219637387201,
+      "grad_norm": 0.6773378252983093,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.0985,
+      "step": 46
+    },
+    {
+      "epoch": 0.0622568093385214,
+      "grad_norm": 0.7034523487091064,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.1289,
+      "step": 47
+    },
+    {
+      "epoch": 0.06358142230317079,
+      "grad_norm": 0.6909533143043518,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.1907,
+      "step": 48
+    },
+    {
+      "epoch": 0.06490603526782018,
+      "grad_norm": 0.6846153140068054,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.3057,
+      "step": 49
+    },
+    {
+      "epoch": 0.06623064823246957,
+      "grad_norm": 0.9431920647621155,
+      "learning_rate": 0.0,
+      "loss": 1.5908,
+      "step": 50
+    },
+    {
+      "epoch": 0.06623064823246957,
+      "eval_loss": 1.2570868730545044,
+      "eval_runtime": 104.7765,
+      "eval_samples_per_second": 48.541,
+      "eval_steps_per_second": 6.07,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null