Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19df8cfb4fb263762edd35195481b243b0e76f56e98ae181beceb2398a64b8c5
+oid sha256:0eaa78125bda7d33136efb8a10cfa409a8585764cc0f6513e9713277435f2a1c
 size 29034840

last-checkpoint/global_step1200/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7892e4165067031a3de1b56c7edb22e4acb83c8cebb89063b4a37ed836cfaba
+size 43429616

last-checkpoint/global_step1200/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31a50405733527ddec68e375cb94d6b768dfc5b360b5bf303000bf791d29c024
+size 43429616

last-checkpoint/global_step1200/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c70b3c612b7514d0d7a693ca84db0e42e21ad94991de26388e9b84eec618a4
+size 43429616

last-checkpoint/global_step1200/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3605344d1a73dbf0f94b59865ef066b003304f7a15a8934b12eeed2bac8c4aa
+size 43429616

last-checkpoint/global_step1200/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4949dd462560313d1eb4ecf7c3f40d8c93afafd740dfad4a692d82208a21705
+size 637299

last-checkpoint/global_step1200/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f37308a1928cd979861c02765c7c0fd2a659975d6ffa2b44d2700d2d3b7af6c
+size 637171

last-checkpoint/global_step1200/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e30460db097248ee05278eb96407926c42431323d285f10fc5e2fd607b330305
+size 637171

last-checkpoint/global_step1200/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bea5a58ffa87d2179402ab01ce1acf03f90486caaa1665a39e4cad2d84367b8
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step1150
+global_step1200

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:274dc3860ee0c7f4d5348f60910a4b568498c04adfefb89f905b1c78a82c1312
+oid sha256:a209a0c0025f9ce8e2beeba50c1f0828d5c34a2482310fcd0bf5fc24c2c67be2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9aa441491b9ca89e796944520fa1db332a67c0a1a920be83edd2d96d741716d
+oid sha256:a67fb929b8c51f9b1c6ff9f11366e57e55128a1d36df85a9d37a008b49017a75
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1ee3434533b24fb771504fa8cceb5c2ea25fe0de1641128feaceccc65afe6ed
+oid sha256:1b9ef3b0c0978d0b611f4257c939f1c2c6f07e6227bfea6675532d285b0b64a7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93b4a44be1335173d2e3120bd0d1e6346f3e832d8935752c70ce1e98f017fa87
+oid sha256:0183d14c8ed52ee533139532e9bcf7bc34ec297a064845b35741cb501d92675f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d461c8d7517d4b88333bff7984fc3bfc149292198b04bbc18a49aee698ffb5c
+oid sha256:16e0cffc6b063574ed312ee2198c86d3dddf2450d0400f042fdc08bd22dcbc7f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6082175970077515,
   "best_model_checkpoint": "saves/CADICA_qwenvl_detect_classify_augmented/lora/sft/checkpoint-1150",
-  "epoch": 0.14088389329576428,
+  "epoch": 0.14700927996079752,
   "eval_steps": 50,
-  "global_step": 1150,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2054,11 +2054,100 @@
       "eval_steps_per_second": 0.78,
       "num_input_tokens_seen": 7889016,
       "step": 1150
+    },
+    {
+      "epoch": 0.1414964319622676,
+      "grad_norm": 5.2350445648477315,
+      "learning_rate": 7.875623046909544e-05,
+      "loss": 0.531,
+      "num_input_tokens_seen": 7922176,
+      "step": 1155
+    },
+    {
+      "epoch": 0.14210897062877095,
+      "grad_norm": 5.184737532915708,
+      "learning_rate": 7.855697251155967e-05,
+      "loss": 0.5251,
+      "num_input_tokens_seen": 7955904,
+      "step": 1160
+    },
+    {
+      "epoch": 0.14272150929527427,
+      "grad_norm": 10.3925643217796,
+      "learning_rate": 7.835703917741212e-05,
+      "loss": 0.613,
+      "num_input_tokens_seen": 7990096,
+      "step": 1165
+    },
+    {
+      "epoch": 0.1433340479617776,
+      "grad_norm": 2.0510833692065225,
+      "learning_rate": 7.81564351951057e-05,
+      "loss": 0.5264,
+      "num_input_tokens_seen": 8024344,
+      "step": 1170
+    },
+    {
+      "epoch": 0.14394658662828091,
+      "grad_norm": 4.531421525747291,
+      "learning_rate": 7.795516530895414e-05,
+      "loss": 0.4993,
+      "num_input_tokens_seen": 8059128,
+      "step": 1175
+    },
+    {
+      "epoch": 0.14455912529478424,
+      "grad_norm": 2.3009325888627155,
+      "learning_rate": 7.775323427901993e-05,
+      "loss": 0.5187,
+      "num_input_tokens_seen": 8092072,
+      "step": 1180
+    },
+    {
+      "epoch": 0.14517166396128756,
+      "grad_norm": 6.253270602192802,
+      "learning_rate": 7.755064688100171e-05,
+      "loss": 0.5339,
+      "num_input_tokens_seen": 8125568,
+      "step": 1185
+    },
+    {
+      "epoch": 0.14578420262779088,
+      "grad_norm": 3.5757925641211483,
+      "learning_rate": 7.734740790612136e-05,
+      "loss": 0.5192,
+      "num_input_tokens_seen": 8159296,
+      "step": 1190
+    },
+    {
+      "epoch": 0.1463967412942942,
+      "grad_norm": 4.569421141701825,
+      "learning_rate": 7.714352216101055e-05,
+      "loss": 0.4876,
+      "num_input_tokens_seen": 8192992,
+      "step": 1195
+    },
+    {
+      "epoch": 0.14700927996079752,
+      "grad_norm": 5.452661792444726,
+      "learning_rate": 7.693899446759727e-05,
+      "loss": 0.4855,
+      "num_input_tokens_seen": 8226648,
+      "step": 1200
+    },
+    {
+      "epoch": 0.14700927996079752,
+      "eval_loss": 0.7277763485908508,
+      "eval_runtime": 19.1608,
+      "eval_samples_per_second": 3.131,
+      "eval_steps_per_second": 0.783,
+      "num_input_tokens_seen": 8226648,
+      "step": 1200
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 7889016,
+  "num_input_tokens_seen": 8226648,
   "num_train_epochs": 1,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -2073,7 +2162,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 496216376475648.0,
+  "total_flos": 517381617090560.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null