Training in progress, step 463

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_cache": null,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec57eae56c6ce15255d58ed5deecddb95d225c0da013b877d93896252cce7730
+size 1976163472

runs/Apr17_19-55-53_gcn22.local.snellius.surf.nl/events.out.tfevents.1744912570.gcn22.local.snellius.surf.nl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c0be3734885639dad2a98ab09483504da8bd5b32a3f53b3185c7472d7d566a8
+size 17773

runs/Apr17_20-05-28_gcn22.local.snellius.surf.nl/events.out.tfevents.1744913133.gcn22.local.snellius.surf.nl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0665424df40d12f7dd293e86b5409ea585bac47e3fab414c9e8f3c99720d7d46
+size 8338

runs/Apr17_20-14-39_gcn113.local.snellius.surf.nl/events.out.tfevents.1744913684.gcn113.local.snellius.surf.nl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e29e3e030ac31bac5eb7d6bcca9dc77112196e656db1916bea19db6db713ee00
+size 61823

runs/Apr18_15-14-36_gcn18.local.snellius.surf.nl/events.out.tfevents.1744982087.gcn18.local.snellius.surf.nl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40521746691970fe78af7b028bf87d22926de58debb8c4906a9683713d487a0b
+size 6140

runs/Apr18_15-20-22_gcn130.local.snellius.surf.nl/events.out.tfevents.1744982430.gcn130.local.snellius.surf.nl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d3a54da03d18ea645a6ab1b09e948953866900054465cd7f4e46568f8694ebb
+size 6141

runs/Apr18_15-25-57_gcn121.local.snellius.surf.nl/events.out.tfevents.1744982766.gcn121.local.snellius.surf.nl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd1e73ff93fe211c520ad7b840deaa6957648ca4a43ad37ab7ca6861e1a8936a
+size 6142

runs/Apr18_15-31-31_gcn129.local.snellius.surf.nl/events.out.tfevents.1744983107.gcn129.local.snellius.surf.nl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:806f7b00d41f18b51efcd28392700303ea56c18d2b1444ad1bb5fb5790d3edd4
+size 6142

runs/Apr18_15-39-57_gcn130.local.snellius.surf.nl/events.out.tfevents.1744983606.gcn130.local.snellius.surf.nl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:604aeef16d635372100a7e978a9f34b9cd06d105624ba9a464a24779b643cd07
+size 6141

runs/Apr18_15-42-01_gcn130.local.snellius.surf.nl/events.out.tfevents.1744983727.gcn130.local.snellius.surf.nl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d397175a14ade20460e200192742ae83bfb0060b1ea7d4af7c2f285f68f641
+size 6140

runs/Apr18_15-45-44_gcn146.local.snellius.surf.nl/events.out.tfevents.1744983949.gcn146.local.snellius.surf.nl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c946f6a4bc7ecb14dc79181ca3e6be1c18d63c1294dc1c08d44c6eb190590ff
+size 6140

runs/Apr18_15-53-23_gcn121.local.snellius.surf.nl/events.out.tfevents.1744984409.gcn121.local.snellius.surf.nl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52876dffce95f761d9c8b979145fd5d933818c739f3109e751e3850cd2c2dfe0
+size 6139

runs/Apr18_15-55-35_gcn128.local.snellius.surf.nl/events.out.tfevents.1744984541.gcn128.local.snellius.surf.nl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:360db2e7a37b8a376b24454b0908bc1b4ff4bb533a952c8f616b0250e344a023
+size 6139

runs/Apr18_15-59-13_gcn128.local.snellius.surf.nl/events.out.tfevents.1744984757.gcn128.local.snellius.surf.nl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21b769d2766c9e9d151222dea9eb8359b05ff26092f305c0c0e2dc91fdbbedbd
+size 6139

runs/Apr18_16-03-09_gcn129.local.snellius.surf.nl/events.out.tfevents.1744984995.gcn129.local.snellius.surf.nl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13174c451bddc58230e5dee658160a12db18623ae4ef9cf71516666da2e406ee
+size 6139

runs/Apr18_16-14-57_gcn133.local.snellius.surf.nl/events.out.tfevents.1744985707.gcn133.local.snellius.surf.nl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c36e2a19af789df10964230b3d38eb7646e64759932c190e4ec353f8fe93c2b
+size 61822

runs/Apr18_17-22-17_gcn148.local.snellius.surf.nl/events.out.tfevents.1744989743.gcn148.local.snellius.surf.nl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db0a6832b6d78b7c2ff81e239b5292c1f9a51d78304c92ed8b9f350029724fe4
+size 57350

runs/Apr18_18-38-47_gcn122.local.snellius.surf.nl/events.out.tfevents.1744994339.gcn122.local.snellius.surf.nl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51b9ed4ce493e54b8523f7c3d4e3cf3538dfbb02fae1502aa44c2c04fdeb1fef
+size 58611

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c852534ad33d333aa478034d64cd37cb14da033a24674c4b2518300f488efa
+size 11418433

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ebe5ddeb499e08a49e27bf5fc10e90782e1d9fde4e0d5862095b1e8c60510c
+size 6328